Upload 7 files

flag/RVT_Area.txt

@@ -0,0 +1,148 @@
+港島 ns
+中西區 ns
+堅尼地城 ns
+石塘咀 ns
+西營盤 ns
+上環 ns
+中環 ns
+金鐘 ns
+半山區 ns
+山頂 ns
+灣仔 ns
+灣仔 ns
+銅鑼灣 ns
+跑馬地 ns
+大坑 ns
+掃桿埔 ns
+渣甸山 ns
+東區 ns
+天后 ns
+寶馬山 ns
+北角 ns
+鰂魚涌 ns
+西灣河 ns
+筲箕灣 ns
+柴灣 ns
+小西灣 ns
+南區 ns
+薄扶林 ns
+香港仔 ns
+鴨脷洲 ns
+黃竹坑 ns
+壽臣山 ns
+淺水灣 ns
+舂磡角 ns
+赤柱 ns
+大潭 ns
+石澳 ns
+九龍 ns
+油尖旺 ns
+尖沙咀 ns
+油麻地 ns
+西九龍填海區 ns
+京士柏 ns
+旺角 ns
+大角咀 ns
+深水埗 ns
+美孚 ns
+荔枝角 ns
+長沙灣 ns
+深水埗 ns
+石硤尾 ns
+又一村 ns
+大窩坪 ns
+昂船洲 ns
+九龍城 ns
+紅磡 ns
+土瓜灣 ns
+馬頭角 ns
+馬頭圍 ns
+啟德 ns
+九龍城 ns
+何文田 ns
+九龍塘 ns
+筆架山 ns
+黃大仙 ns
+新蒲崗 ns
+黃大仙 ns
+東頭 ns
+橫頭磡 ns
+樂富 ns
+鑽石山 ns
+慈雲山 ns
+牛池灣 ns
+觀塘 ns
+坪石 ns
+九龍灣 ns
+牛頭角 ns
+佐敦谷 ns
+觀塘 ns
+秀茂坪 ns
+藍田 ns
+油塘 ns
+鯉魚門 ns
+葵青 ns
+葵涌 ns
+青衣 ns
+荃灣 ns
+荃灣 ns
+梨木樹 ns
+汀九 ns
+深井 ns
+青龍頭 ns
+馬灣 ns
+欣澳 ns
+新界 ns
+屯門 ns
+大欖涌 ns
+掃管笏 ns
+屯門 ns
+藍地 ns
+元朗 ns
+洪水橋 ns
+廈村 ns
+流浮山 ns
+天水圍 ns
+元朗 ns
+新田 ns
+落馬洲 ns
+錦田 ns
+石崗 ns
+八鄉 ns
+北區 ns
+粉嶺 ns
+聯和墟 ns
+上水 ns
+石湖墟 ns
+沙頭角 ns
+鹿頸 ns
+烏蛟騰 ns
+大埔 ns
+大埔墟 ns
+大埔 ns
+大埔滘 ns
+大尾篤 ns
+船灣 ns
+樟木頭 ns
+企嶺下 ns
+沙田 ns
+大圍 ns
+沙田 ns
+火炭 ns
+馬料水 ns
+烏溪沙 ns
+馬鞍山 ns
+西貢 ns
+清水灣 ns
+西貢 ns
+大網仔 ns
+將軍澳 ns
+坑口 ns
+調景嶺 ns
+馬游塘 ns
+離島 ns
+長洲 ns
+坪洲 ns
+大嶼山 ns
+東涌 ns
+南丫島 ns

main.py

@@ -0,0 +1,161 @@
+import gradio as gr
+import jieba
+import jieba.analyse
+import aiohttp
+import asyncio
+import ssl
+from aiohttp import ClientSession
+
+ssl_context = ssl.create_default_context()
+ssl_context.check_hostname = False
+ssl_context.verify_mode = ssl.CERT_NONE
+
+def setup_jieba_dictionaries():
+    dictionaries = [
+        'flag/RVT_AddressCh.txt',
+        'flag/RVT_AddressEn.txt',
+        'flag/RVT_Area.txt',
+        'flag/RVT_BuildingCh.txt',
+        'flag/RVT_BuildingEn.txt'
+    ]
+    for file_path in dictionaries:
+        jieba.load_userdict(file_path)
+
+def process_text(text):
+    setup_jieba_dictionaries()
+
+    user_dict_terms = set()
+    for file_path in [
+        'flag/RVT_AddressCh.txt',
+        'flag/RVT_AddressEn.txt',
+        'flag/RVT_Area.txt',
+        'flag/RVT_BuildingCh.txt',
+        'flag/RVT_BuildingEn.txt'
+    ]:
+        try:
+            with open(file_path, 'r', encoding='utf-8') as f:
+                user_dict_terms.update(line.strip().split()[0] for line in f)
+        except FileNotFoundError:
+            print(f'File not found: {file_path}')
+        except Exception as e:
+            print(f'Error reading file {file_path}: {e}')
+
+    lines = text.splitlines()
+    results = []
+
+    for line in lines:
+        line = line.strip()
+        keywords = jieba.analyse.textrank(line, topK=20, withWeight=False, allowPOS=('ns', 'n', 'vn', 'v'))
+        keyword_text = ' '.join(keyword for keyword in keywords if keyword in user_dict_terms)
+        results.append(keyword_text)
+
+    return results
+
+def reformat_text(text):
+    lines = text.splitlines()
+    return [line.strip() for line in lines if line.strip()]
+
+def process_text_only(text, reformat):
+    extracted_keywords = process_text(text)
+    if reformat:
+        extracted_keywords = reformat_text('\n'.join(extracted_keywords))
+    # Join keywords with newline characters
+    return '\n'.join(extracted_keywords)
+
+async def lookup_address(query, language='zh-Hant'):
+    url = 'https://www.als.gov.hk/lookup'
+    headers = {
+        'Accept': 'application/json',
+        'Accept-Language': language
+    }
+    payload = {
+        'q': query
+    }
+
+    async with ClientSession() as session:
+        try:
+            async with session.post(url, headers=headers, data=payload, ssl=ssl_context) as response:
+                if response.status == 200:
+                    return await response.json()
+                else:
+                    print(f'Error fetching data: Status Code {response.status}')
+                    return {'error': f'Error fetching data: Status Code {response.status}'}
+        except aiohttp.ClientError as e:
+            print(f'Client Error: {e}')
+            return {'error': f'Client Error: {e}'}
+        except Exception as e:
+            print(f'General Error: {e}')
+            return {'error': f'General Error: {e}'}
+
+async def get_address_lookup_results(keywords):
+    results = []
+    for keyword in keywords:
+        keyword = keyword.strip()
+        if not keyword:  # Skip empty keywords
+            continue
+        lookup_results = await lookup_address(keyword)
+        if 'SuggestedAddress' in lookup_results and isinstance(lookup_results['SuggestedAddress'], list):
+            first_match = lookup_results['SuggestedAddress'][0]  # Use the first match
+            full_address = 'No matches found'
+            geo_address = 'N/A'
+            latitude = 'N/A'
+            longitude = 'N/A'
+            matched_building = 'No Building Name'
+
+            if first_match:
+                premises_address = first_match['Address']['PremisesAddress']
+                raw_address = premises_address.get('ChiPremisesAddress', {})
+                matched_building = raw_address.get('BuildingName', 'No Building Name')
+                full_address = matched_building
+                geo_address = premises_address.get('GeoAddress', 'N/A')
+                geo_info = premises_address.get('GeospatialInformation', {})
+                latitude = geo_info.get('Latitude', 'N/A')
+                longitude = geo_info.get('Longitude', 'N/A')
+
+            results.append({
+                'Keyword': keyword,
+                'Full Address': full_address,
+                'Geo Address': geo_address,
+                'Latitude': latitude,
+                'Longitude': longitude
+            })
+        else:
+            results.append({
+                'Keyword': keyword,
+                'Full Address': 'No matches found',
+                'Geo Address': 'N/A',
+                'Latitude': 'N/A',
+                'Longitude': 'N/A'
+            })
+
+    return results
+
+async def gradio_function(text, reformat, perform_lookup):
+    extracted_keywords = process_text_only(text, reformat)
+    keywords_list = extracted_keywords.splitlines()
+
+    address_results = []
+    if perform_lookup:
+        address_results = await get_address_lookup_results(keywords_list)
+
+    return extracted_keywords, address_results
+
+def gradio_interface(text, reformat, perform_lookup):
+    return asyncio.run(gradio_function(text, reformat, perform_lookup))
+
+interface = gr.Interface(
+    fn=gradio_interface,
+    inputs=[
+        gr.Textbox(lines=20, placeholder="Paste text here, each line will be processed separately..."),
+        gr.Checkbox(label="Reformat text (remove empty lines)"),
+        gr.Checkbox(label="Perform Address Lookup")
+    ],
+    outputs=[
+        gr.Textbox(label="Extracted Address Keywords"),
+        gr.JSON(label="Address Lookup Results")
+    ],
+    title="Address Extraction and Lookup with Natural Language Processing",
+    description="Extract address keywords using NLP and optionally perform address lookup using ALS."
+)
+
+interface.launch()

requirements.txt

@@ -0,0 +1,4 @@
+aiohttp==3.9.5
+aiohttp==3.10.3
+gradio==4.41.0
+jieba==0.42.1