PgsFile 0.4.9__py3-none-any.whl → 0.5.1__py3-none-any.whl

PgsFile/PgsFile.py

@@ -4142,3 +4142,142 @@ def tfidf_keyword_extraction(documents, top_percent=(0.0, 0.10)):
 
     return full_list, candidates
 
+
+from xml.dom.minidom import Document
+from datetime import datetime
+def maketmx(
+    tmx_path,
+    source_list,
+    target_list,
+    source_lang="zh-CN",
+    target_lang="en-US",
+    author="Petercusin",
+    client_name=None,
+    project_id=None,
+    domain=None,
+    status="Final"
+):
+    """
+    Generate a TMX (Translation Memory eXchange) file for any two language pairs, with optional metadata.
+
+    Parameters
+    ----------
+    tmx_path : str
+        Path to save the TMX file, e.g., "translation_memory.tmx".
+    source_list : list of str
+        List of source language segments, e.g., ["你好", "再见"].
+    target_list : list of str
+        List of target language segments, e.g., ["Hello", "Goodbye"].
+        **Must have the same number of elements as `source_list`.**
+    source_lang : str, optional
+        Source language code, e.g., "zh-CN" (default), "fr-FR", "de-DE".
+    target_lang : str, optional
+        Target language code, e.g., "en-US" (default), "es-ES", "ja-JP".
+    author : str, optional
+        Author of the TMX file, e.g., "Petercusin" (default).
+    client_name : str, optional
+        Name of the client or company, e.g., "Acme Corp".
+    project_id : str, optional
+        Project identifier, e.g., "Project_XYZ_2025".
+    domain : str, optional
+        Domain or subject field, e.g., "Medical", "Legal", "Technical".
+    status : str, optional
+        Translation status, e.g., "Draft", "Reviewed", "Final" (default).
+
+    Returns
+    -------
+    None
+        Writes the TMX file to the specified path.
+
+    Raises
+    ------
+    ValueError
+        If `source_list` and `target_list` have different lengths.
+
+    Example
+    -------
+    # Chinese to English, with metadata
+    maketmx(
+        "zh_en.tmx",
+        ["你好", "再见"],
+        ["Hello", "Goodbye"],
+        "zh-CN",
+        "en-US",
+        author="Dr. Guisheng PAN",
+        client_name="Acme Corp",
+        project_id="Project_XYZ_2025",
+        domain="Technical",
+        status="Final"
+    )
+    """
+    if len(source_list) != len(target_list):
+        raise ValueError("source_list and target_list must have the same number of elements.")
+
+    doc = Document()
+    tmx = doc.createElement("tmx")
+    tmx.setAttribute("version", "1.4")
+    doc.appendChild(tmx)
+
+    header = doc.createElement("header")
+    header.setAttribute("creationtool", "PgsFile")
+    header.setAttribute("creationtoolversion", "0.5.1")
+    header.setAttribute("creationtooldeveloper", author)
+    header.setAttribute("creationdate", datetime.now().strftime("%Y-%m-%dT%H:%M:%SZ"))
+    header.setAttribute("srclang", source_lang)
+    header.setAttribute("trtlang", target_lang)
+    header.setAttribute("datatype", "plaintext")
+    header.setAttribute("segtype", "sentence")
+    header.setAttribute("adminlang", "en-US")
+    header.setAttribute("o-tmf", "PgsFile_TM")
+    tmx.appendChild(header)
+
+    # Add optional metadata as <prop> elements
+    if client_name:
+        prop = doc.createElement("prop")
+        prop.setAttribute("type", "x-Client")
+        prop.appendChild(doc.createTextNode(client_name))
+        header.appendChild(prop)
+    if project_id:
+        prop = doc.createElement("prop")
+        prop.setAttribute("type", "x-Project")
+        prop.appendChild(doc.createTextNode(project_id))
+        header.appendChild(prop)
+    if domain:
+        prop = doc.createElement("prop")
+        prop.setAttribute("type", "x-Domain")
+        prop.appendChild(doc.createTextNode(domain))
+        header.appendChild(prop)
+    if status:
+        prop = doc.createElement("prop")
+        prop.setAttribute("type", "x-Status")
+        prop.appendChild(doc.createTextNode(status))
+        header.appendChild(prop)
+
+    body = doc.createElement("body")
+    tmx.appendChild(body)
+
+    for i in range(len(source_list)):
+        tu = doc.createElement("tu")
+        body.appendChild(tu)
+
+        # Source language segment
+        tuv = doc.createElement("tuv")
+        tuv.setAttribute("xml:lang", source_lang)
+        tu.appendChild(tuv)
+        seg = doc.createElement("seg")
+        seg_text = doc.createTextNode(source_list[i])
+        seg.appendChild(seg_text)
+        tuv.appendChild(seg)
+
+        # Target language segment
+        tuv = doc.createElement("tuv")
+        tuv.setAttribute("xml:lang", target_lang)
+        tu.appendChild(tuv)
+        seg = doc.createElement("seg")
+        seg_text = doc.createTextNode(target_list[i])
+        seg.appendChild(seg_text)
+        tuv.appendChild(seg)
+
+    with open(tmx_path, 'w', encoding='utf-8') as f:
+        doc.writexml(f, indent='\t', newl='\n', addindent='\t')
+

PgsFile/__init__.py

@@ -19,6 +19,7 @@ from .PgsFile import mhtml2html
 # 4. Text data storage
 from .PgsFile import write_to_txt, write_to_excel, write_to_json, write_to_json_lines, append_dict_to_json, save_dict_to_excel, file_to_list_of_dicts
 from .PgsFile import write_to_excel_normal
+from .PgsFile import maketmx
 
 # 5. File/folder process
 from .PgsFile import FilePath, FileName, DirList

{PgsFile-0.4.9.dist-info → PgsFile-0.5.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PgsFile
-Version: 0.4.9
+Version: 0.5.1
 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://mp.weixin.qq.com/s/lWMkYDWQMjBJNKY2vMYTpw
 Author: Pan Guisheng
@@ -31,7 +31,7 @@ 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, and JSON lines.
+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.

{PgsFile-0.4.9.dist-info → PgsFile-0.5.1.dist-info}/RECORD

@@ -1,5 +1,5 @@
-PgsFile/PgsFile.py,sha256=3iyfFE5THgwwz0_MtylUlMn-72gsRaCbUxdm9LcI8nQ,169903
-PgsFile/__init__.py,sha256=mWZ8dfTlzeCfTHFlWyHY3vCwqyM4_YQBGPd6vBoNGso,3674
+PgsFile/PgsFile.py,sha256=YzdCEPFvT1jisKcihRUNyi2hqAWhStkP-yIcj_xqiLI,174646
+PgsFile/__init__.py,sha256=YkDTLWtveSeN4I5ZXSmdp7YZFOHb4yEzxQB82DEHk9s,3704
 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
@@ -2593,8 +2593,8 @@ PgsFile/models/prompts/5. ATE prompt.txt,sha256=5wu0gGlsV7DI0LruYM3-uAC6brppyYD0
 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-0.4.9.dist-info/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
-PgsFile-0.4.9.dist-info/METADATA,sha256=kz9wjDsNe156XAqCCKTveiOLPnvkOGbbjR1j8NkRNaM,3065
-PgsFile-0.4.9.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-PgsFile-0.4.9.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
-PgsFile-0.4.9.dist-info/RECORD,,
+PgsFile-0.5.1.dist-info/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
+PgsFile-0.5.1.dist-info/METADATA,sha256=AcQetbNOrw-Celapsr7Lz5P_CzikMR1jwf6OENgyUNU,3070
+PgsFile-0.5.1.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+PgsFile-0.5.1.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
+PgsFile-0.5.1.dist-info/RECORD,,