PgsFile 0.5.2__py3-none-any.whl → 0.5.4__py3-none-any.whl

PgsFile/PgsFile.py

@@ -4281,3 +4281,82 @@ def maketmx(
     with open(tmx_path, 'w', encoding='utf-8') as f:
         doc.writexml(f, indent='\t', newl='\n', addindent='\t')
 
+raw_translation_prompts = {
+    "general": {
+        "basic": "Act as a professional Chinese–English translator specializing in finance and economics. Translate the following text: {text}",
+        "formal_report": "Translate the following Chinese text into English, targeting an international audience with a formal tone suitable for a financial report: {text}",
+        "social_media": "Translate the following Chinese text into English, keeping a friendly and approachable tone suitable for social media content about finance: {text}",
+    },
+    "technical": {
+        "regulation": "Translate the following Chinese financial regulation into English, using terminology consistent with the People’s Bank of China (PBC) and international financial standards. Maintain a formal tone: {text}",
+        "contract": "Translate the following Chinese financial contract into English, ensuring consistency with financial and legal terminology, particularly in capital markets: {text}",
+        "glossary": "Translate the following Chinese text into English using the attached glossary and reference websites: {glossary}, {urls}. Text: {text}"
+    },
+    "review": {
+        "proofread": "Proofread the following Chinese-to-English machine translation. Correct grammar, syntax, and financial terminology errors, and improve readability while maintaining the original meaning: {text}",
+        "localize": "Review the following Chinese-to-English translation as a native English speaker. Adjust any phrases to ensure they sound natural and localized for an international finance audience: {text}",
+        "back_translate": "Back-translate the following English text into Chinese as literally as possible, without interpreting meaning: {text}"
+    },
+    "creative": {
+        "idiom": "How would an English speaker naturally express the Chinese economic idiom: {text}?",
+        "slogan": "Transcreate the following Chinese financial advertising slogan into English. Maintain its persuasive impact and cultural relevance while keeping it concise and memorable. Provide two versions and explain your choices: {text}"
+    }
+}
+
+RESULT_ONLY_NOTE = " Only return the translation result without any further explanations."
+
+def append_result_only(prompts_dict, note=RESULT_ONLY_NOTE):
+    """
+    Recursively append the note to all prompt strings in a nested dict.
+    """
+    updated = {}
+    for key, value in prompts_dict.items():
+        if isinstance(value, dict):
+            updated[key] = append_result_only(value, note)
+        elif isinstance(value, str):
+            updated[key] = value.strip() + note
+        else:
+            updated[key] = value
+    return updated
+
+# Apply it
+translation_prompts = append_result_only(raw_translation_prompts)
+
+
+def csv_to_json_append(csv_path: str, json_path: str) -> None:
+    """
+    Convert a CSV file into a list of dictionaries and append them into a JSON file.
+
+    Args:
+        csv_path (str): Path to the CSV file.
+        json_path (str): Path to the output JSON file.
+    """
+    
+    import pandas as pd
+    
+    # Load CSV into DataFrame
+    df = pd.read_csv(csv_path)
+
+    # Automatically get all columns, convert to list of dicts
+    data_list = df.to_dict(orient='records')
+
+    # Append each dict to JSON file
+    for record in data_list:
+        append_dict_to_json(json_path, record)
+
+    print(f"✅ Completed! Appended {len(data_list)} records to {json_path}")
+    
+def get_data_csv(csv_path: str) -> list[dict]:
+    """
+    Load a CSV file and return its rows as a list of dictionaries.
+    Column names are automatically detected.
+
+    Args:
+        csv_path (str): Path to the CSV file.
+
+    Returns:
+        list[dict]: A list of dictionaries, where each dict represents one row.
+    """
+    import pandas as pd
+    df = pd.read_csv(csv_path)
+    return df.to_dict(orient="records")    

PgsFile/__init__.py

@@ -11,7 +11,7 @@ from .PgsFile import conda_mirror_commands
 
 # 3. Text data retrieval
 from .PgsFile import get_data_text, get_data_lines, get_json_lines, get_tsv_lines
-from .PgsFile import get_data_excel, get_data_json, get_data_tsv, extract_misspelled_words_from_docx
+from .PgsFile import get_data_excel, get_data_json, get_data_tsv, get_data_csv, extract_misspelled_words_from_docx
 from .PgsFile import get_data_html_online, get_data_html_offline
 from .PgsFile import get_data_table_url, get_data_table_html_string
 from .PgsFile import mhtml2html
@@ -33,6 +33,7 @@ from .PgsFile import set_permanent_environment_variable
 from .PgsFile import delete_permanent_environment_variable
 from .PgsFile import get_env_variable, get_all_env_variables
 from .PgsFile import get_system_info
+from .PgsFile import csv_to_json_append
 
 # 6. Data cleaning
 from .PgsFile import BigPunctuation, StopTags, Special, yhd
@@ -55,6 +56,7 @@ from .PgsFile import extract_noun_phrases, get_LLMs_prompt, extract_keywords_en,
 from .PgsFile import extract_dependency_relations, extract_dependency_relations_full
 from .PgsFile import predict_category
 from .PgsFile import tfidf_keyword_extraction
+from .PgsFile import translation_prompts
 
 # 8. Maths
 from .PgsFile import len_rows, check_empty_cells

PgsFile/models/prompts/9. TextClassification prompt.txt

@@ -0,0 +1,32 @@
+You are an expert text classifier.
+Your task is to classify a given Chinese news text into ONE and ONLY ONE of the following categories:
+
+Categories:
+- 港澳台 (Hong Kong, Macao, Taiwan)
+- 房产 (Real Estate)
+- 军事 (Military)
+- 社会 (Society)
+- 财经 (Finance & Economy)
+- 文娱 (Culture & Entertainment)
+- 汽车 (Automobile)
+- 国际 (International News)
+- 教育 (Education)
+- 健康 (Health)
+- 美食 (Food & Cuisine)
+- 时政 (Current Affairs / Politics)
+- 法治 (Law & Legal Affairs)
+- 旅游 (Travel & Tourism)
+- 体育 (Sports)
+- 数码科技 (Digital Technology)
+- 动漫 (Anime & Comics)
+- 反腐前沿 (Anti-Corruption)
+- 国内 (Domestic News within Mainland China)
+
+Instructions:
+1. Read the input Chinese text carefully.
+2. Determine the most relevant SINGLE category from the list above.
+3. If multiple categories seem relevant, choose the one that best represents the MAIN topic of the text.
+4. Output ONLY the category name in Chinese (e.g., 财经, 体育), without explanation.
+
+Text to classify:
+{text}

pgsfile-0.5.4.dist-info/METADATA

@@ -0,0 +1,65 @@
+Metadata-Version: 2.4
+Name: PgsFile
+Version: 0.5.4
+Summary: This module streamlines Python package management, script execution, file handling, web scraping, and multimedia downloads. It supports LLM-based NLP tasks like OCR, tokenization, lemmatization, POS tagging, NER, ATE, dependency parsing, MDD, WSD, LIWC, MIP analysis, text classification, and Chinese-English sentence alignment. Additionally, it generates word lists and data visualizations, making it a practical tool for data scraping and analysis—ideal for literary students and researchers.
+Author-email: Pan Guisheng <panguisheng@sufe.edu.cn>
+License: License :: Free For Educational Use
+        
+        Copyright (c) 2021-present, GIIT, Shanghai International Studies University.
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Project-URL: Homepage, https://github.com/Petercusin/PgsFile
+Project-URL: Repository, https://github.com/Petercusin/PgsFile
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: Free For Educational Use
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: chardet
+Requires-Dist: pandas
+Requires-Dist: python-docx
+Requires-Dist: pip
+Requires-Dist: requests
+Requires-Dist: fake-useragent
+Requires-Dist: lxml
+Requires-Dist: pimht
+Requires-Dist: pysbd
+Requires-Dist: nlpir-python
+Requires-Dist: pillow
+Requires-Dist: liwc
+Dynamic: license-file
+
+Purpose: This module is designed to make complex tasks accessible and convenient, even for beginners. By providing a unified set of tools, it simplifies the workflow for data collection, processing, and analysis. Whether you're scraping data from the web, cleaning text, or performing LLM-based NLP tasks, this module ensures you can focus on your research without getting bogged down by technical challenges.
+
+Key Features:
+1. **Web Scraping:** Easily scrape data from websites and download multimedia content.
+2. **Package Management:** Install, uninstall, and manage Python packages with simple commands.
+3. **Data Retrieval:** Extract data from various file formats like text, JSON, CSV, TSV, XLSX, XML, and HTML (both online and offline).
+4. **Data Storage:** Write and append data to text files, Excel, JSON, TMX, and JSON lines.
+5. **File and Folder Processing:** Manage file paths, create directories, move or copy files, convert CSV to JSON, and search for files with specific keywords.
+6. **Data Cleaning:** Clean text, handle punctuation, remove stopwords, convert Markdown strings into Python objects, and prepare data for analysis, utilizing valuable corpora and dictionaries such as CET-4/6 vocabulary, BE21 and BNC-COCA word lists.
+7. **NLP:** Perform OCR, word tokenization, lemmatization, POS tagging, NER, dependency parsing, ATE, MDD, WSD, LIWC, MIP analysis, text classification, and Chinese-English sentence alignment using prepared LLM prompts.
+8. **Math Operations:** Format numbers, convert decimals to percentages, and validate data.
+9. **Visualization:** Process images (e.g., make white pixels transparent, resize images) and manage fonts for rendering text.
+
+Author: Pan Guisheng, a PhD student at the Graduate Institute of Interpretation and Translation of Shanghai International Studies University
+Email: 895284504@qq.com
+Homepage: https://mp.weixin.qq.com/s/lWMkYDWQMjBJNKY2vMYTpw

{PgsFile-0.5.2.dist-info → pgsfile-0.5.4.dist-info}/RECORD

@@ -1,5 +1,5 @@
-PgsFile/PgsFile.py,sha256=YzdCEPFvT1jisKcihRUNyi2hqAWhStkP-yIcj_xqiLI,174646
-PgsFile/__init__.py,sha256=YkDTLWtveSeN4I5ZXSmdp7YZFOHb4yEzxQB82DEHk9s,3704
+PgsFile/PgsFile.py,sha256=BUJJZFngPXiRQ8NQ7k11DdE6trxJrdbLI8mJU5-MFq4,178575
+PgsFile/__init__.py,sha256=g37kKJxGqD61TQCWg6tDhUr27u-XRuMTIYNUjzRLPQ8,3801
 PgsFile/Corpora/Idioms/English_Idioms_8774.txt,sha256=qlsP0yI_XGECBRiPZuLkGZpdasc77sWSKexANu7v8_M,175905
 PgsFile/Corpora/Monolingual/Chinese/People's Daily 20130605/Raw/00000000.txt,sha256=SLGGSMSb7Ff1RoBstsTW3yX2wNZpqEUchFNpcI-mrR4,1513
 PgsFile/Corpora/Monolingual/Chinese/People's Daily 20130605/Raw/00000001.txt,sha256=imOa6UoCOIZoPXT4_HNHgCUJtd4FTIdk2FZNHNBgJyg,3372
@@ -2587,14 +2587,15 @@ PgsFile/models/fonts/博洋行书3500.TTF,sha256=VrgeHr8cgOL6JD05QyuD9ZSyw4J2aIV
 PgsFile/models/fonts/陆柬之行书字体.ttf,sha256=Zpd4Z7E9w-Qy74yklXHk4vM7HOtHuQgllvygxZZ1Hvs,1247288
 PgsFile/models/prompts/1. MIP prompt.txt,sha256=4lHlHmleayRytqr1n9jtt6vn1rQvyf4BKeThpbwI8o8,1638
 PgsFile/models/prompts/2. WSD prompt.txt,sha256=o-ZFtCRUCDrXgm040WTQch9v2Y_r2SIlrZaquilJjgQ,2348
-PgsFile/models/prompts/3. ICTCLAS Prompt.txt,sha256=VFn6N_JViAbyy9NazA8gjX6SGo5mgBcZOf95aC9JB84,592
+PgsFile/models/prompts/3. ICTCLAS prompt.txt,sha256=VFn6N_JViAbyy9NazA8gjX6SGo5mgBcZOf95aC9JB84,592
 PgsFile/models/prompts/4. OCR prompt.txt,sha256=YxUQ2IlE52k0fcBnGsuOHqWAmfiEmIu6iRz5zecQ8dk,260
 PgsFile/models/prompts/5. ATE prompt.txt,sha256=5wu0gGlsV7DI0LruYM3-uAC6brppyYD0IoiFVjMqm5Y,1553
 PgsFile/models/prompts/6. ATE3 prompt.txt,sha256=VnaXpPa6BgZHUcm8PxmP_qgU-8xEoTB3XcBqjwCUy_g,1254
 PgsFile/models/prompts/7. SentAlign prompt.txt,sha256=hXpqqC-CAgo8EytkJ0MaLhevLefALazWriY-ew39jxs,1537
 PgsFile/models/prompts/8. TitleCase prompt.txt,sha256=4p-LfGy0xAj2uPi9amyMm41T6Z17VNpFFsGZOgWhROs,1136
-PgsFile-0.5.2.dist-info/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
-PgsFile-0.5.2.dist-info/METADATA,sha256=fEpBEg0EhJCZOZdSTzLdD5Yn1eRlvdv1YFmWKmM4F2E,3119
-PgsFile-0.5.2.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-PgsFile-0.5.2.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
-PgsFile-0.5.2.dist-info/RECORD,,
+PgsFile/models/prompts/9. TextClassification prompt.txt,sha256=JhQJu3rQSstNtkIkxPR1K-QmH9sGBEhbVKHAi7ItMUA,1066
+pgsfile-0.5.4.dist-info/licenses/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
+pgsfile-0.5.4.dist-info/METADATA,sha256=KtGtZ5Q-o3muHqz5OsKp3ZUQz-qwncC-l65-udjesz8,4555
+pgsfile-0.5.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+pgsfile-0.5.4.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
+pgsfile-0.5.4.dist-info/RECORD,,

{PgsFile-0.5.2.dist-info → pgsfile-0.5.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.44.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

PgsFile-0.5.2.dist-info/METADATA

@@ -1,43 +0,0 @@
-Metadata-Version: 2.1
-Name: PgsFile
-Version: 0.5.2
-Summary: This module simplifies Python package management, script execution, file handling, web scraping, and multimedia downloads. The module supports (LLM-based) NLP tasks such as OCR, tokenization, lemmatization, POS tagging, NER, ATE, dependency parsing, MDD, WSD, LIWC, MIP analysis and Chinese-English sentence alignment. It also generates word lists, and plots data, aiding literary students. Ideal for scraping data, cleaning text, and analyzing language, it offers user-friendly tools to streamline workflows.
-Home-page: https://github.com/Petercusin/PgsFile
-Author: Pan Guisheng
-Author-email: panguisheng@sufe.edu.cn
-License: Educational free
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: Free For Educational Use
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: chardet
-Requires-Dist: pandas
-Requires-Dist: python-docx
-Requires-Dist: pip
-Requires-Dist: requests
-Requires-Dist: fake-useragent
-Requires-Dist: lxml
-Requires-Dist: pimht
-Requires-Dist: pysbd
-Requires-Dist: nlpir-python
-Requires-Dist: pillow
-Requires-Dist: liwc
-
-Purpose: This module is designed to make complex tasks accessible and convenient, even for beginners. By providing a unified set of tools, it simplifies the workflow for data collection, processing, and analysis. Whether you're scraping data from the web, cleaning text, or performing LLM-based NLP tasks, this module ensures you can focus on your research without getting bogged down by technical challenges.
-
-Key Features:
-1. **Web Scraping:** Easily scrape data from websites and download multimedia content.
-2. **Package Management:** Install, uninstall, and manage Python packages with simple commands.
-3. **Data Retrieval:** Extract data from various file formats like text, JSON, TSV, Excel, XML, and HTML (both online and offline).
-4. **Data Storage:** Write and append data to text files, Excel, JSON, TMX, and JSON lines.
-5. **File and Folder Processing:** Manage file paths, create directories, move or copy files, and search for files with specific keywords.
-6. **Data Cleaning:** Clean text, handle punctuation, remove stopwords, convert Markdown strings into Python objects, and prepare data for analysis, utilizing valuable corpora and dictionaries such as CET-4/6 vocabulary, BE21 and BNC-COCA word lists.
-7. **NLP:** Perform OCR, word tokenization, lemmatization, POS tagging, NER, dependency parsing, ATE, MDD, WSD, LIWC, MIP analysis, and Chinese-English sentence alignment using prepared LLM prompts.
-8. **Math Operations:** Format numbers, convert decimals to percentages, and validate data.
-9. **Visualization:** Process images (e.g., make white pixels transparent, resize images) and manage fonts for rendering text.
-
-Author: Pan Guisheng, a PhD student at the Graduate Institute of Interpretation and Translation of Shanghai International Studies University
-Email: 895284504@qq.com
-Homepage: https://mp.weixin.qq.com/s/lWMkYDWQMjBJNKY2vMYTpw