PgsFile 0.5.5__tar.gz → 0.5.7__tar.gz

pgsfile-0.5.7/MANIFEST.in

@@ -0,0 +1,2 @@
+recursive-include PgsFile/Corpora *
+recursive-include PgsFile/models *

{pgsfile-0.5.5/src/PgsFile.egg-info → pgsfile-0.5.7}/PKG-INFO

@@ -1,32 +1,11 @@
 Metadata-Version: 2.4
 Name: PgsFile
-Version: 0.5.5
+Version: 0.5.7
 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
+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
@@ -45,7 +24,17 @@ Requires-Dist: pysbd
 Requires-Dist: nlpir-python
 Requires-Dist: pillow
 Requires-Dist: liwc
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
 Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 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.
 

{pgsfile-0.5.5/src → pgsfile-0.5.7}/PgsFile/PgsFile.py

@@ -5,7 +5,7 @@ Created on Wed Apr 28 23:44:04 2021
 @author: Petercusin
 """
 
-import os, sys
+import os, sys, re
 def check_contain_chinese(check_str):
     for ch in check_str:
         if u'\u4e00' <=ch<= u'\u9fff':
@@ -1774,7 +1774,8 @@ def remove_empty_last_line(folder_path):
         f2.close()
     print(end_empty_files,str(len(end_empty_files))+" files found with last line empty!")
 
-def find_txt_files_with_keyword(root_folder, keyword, case_sensitive=None):
+
+def find_txt_files_with_keyword(root_folder, keyword, case_sensitive=False):
     """
     Find all .txt files whose names contain the specified keyword in a multi-level folder structure.
 
@@ -1784,21 +1785,22 @@ def find_txt_files_with_keyword(root_folder, keyword, case_sensitive=None):
 
     Returns:
         A list of file paths that match the search criteria.
-    """
-    import fnmatch,os
-    matches=[]
-    if case_sensitive is None or case_sensitive==False:
-        for root, dirnames, filenames in os.walk(root_folder):
-            for filename in fnmatch.filter(filenames, '*' + keyword + '*.txt'):
-                matches.append(os.path.join(root, filename))
-    elif case_sensitive==True:
-        import re
-        pattern=re.compile(r'.*' + re.escape(keyword) + r'.*\.txt')
-        for root, dirnames, filenames in os.walk(root_folder):
+    """    
+    import fnmatch
+    matches = []
+    if not case_sensitive:
+        keyword_lower = keyword.lower()
+        for root, _, filenames in os.walk(root_folder):
+            for filename in filenames:
+                if filename.lower().endswith(".txt") and keyword_lower in filename.lower():
+                    matches.append(os.path.join(root, filename))
+    else:
+        pattern = re.compile(r'.*' + re.escape(keyword) + r'.*\.txt')
+        for root, _, filenames in os.walk(root_folder):
             for filename in filenames:
                 if pattern.match(filename):
                     matches.append(os.path.join(root, filename))
-    return matches    
+    return matches
 
 import fnmatch
 def find_user_files_in_upper_folder(directory, user_file_name):
@@ -3364,7 +3366,7 @@ def get_all_env_variables():
     return dict(env_vars)
 
 import subprocess
-def set_permanent_environment_variable(variable_name, variable_value, system_wide=False):
+def set_permanent_env_var_win(variable_name, variable_value, system_wide=False):
     """
     Sets a permanent environment variable on Windows using the `setx` command.
 
@@ -3390,7 +3392,7 @@ def set_permanent_environment_variable(variable_name, variable_value, system_wid
     except Exception as e:
         print(f'An error occurred: {e}')
 
-def delete_permanent_environment_variable(variable_name, system_wide=False):
+def delete_permanent_env_var_win(variable_name, system_wide=False):
     """
     Deletes a permanent environment variable on Windows using the `reg` command.
 
@@ -3421,6 +3423,53 @@ def delete_permanent_environment_variable(variable_name, system_wide=False):
         print(f'An error occurred: {e}')
 
 
+def set_permanent_env_var_mac(var_name: str, var_value: str, shell_config: str = "~/.zshrc") -> None:
+    """
+    Sets a permanent environment variable by appending it to the specified shell configuration file.
+
+    Args:
+        var_name (str): Name of the environment variable.
+        var_value (str): Value of the environment variable.
+        shell_config (str): Path to the shell configuration file (e.g., "~/.zshrc", "~/.bashrc").
+                           Defaults to "~/.zshrc".
+    """
+    shell_config = os.path.expanduser(shell_config)
+
+    # Append the export line to the shell config file
+    with open(shell_config, "a") as f:
+        f.write(f'\nexport {var_name}="{var_value}"\n')
+
+    print(f'Added {var_name} to {shell_config}.')
+    print(f'Restart your shell or run: source {shell_config}')
+
+
+def delete_permanent_env_var_mac(var_name: str, shell_config: str = "~/.zshrc") -> None:
+    """
+    Deletes a permanent environment variable from the specified shell configuration file.
+
+    Args:
+        var_name (str): Name of the environment variable to delete.
+        shell_config (str): Path to the shell configuration file (e.g., "~/.zshrc", "~/.bashrc").
+                           Defaults to "~/.zshrc".
+    """
+    shell_config = os.path.expanduser(shell_config)
+
+    # Read the file and remove the line containing the export statement
+    with open(shell_config, "r") as f:
+        lines = f.readlines()
+
+    # Use regex to find and remove the line
+    pattern = re.compile(rf'^\s*export\s+{var_name}=.*$\n?', re.MULTILINE)
+    new_lines = [line for line in lines if not pattern.match(line)]
+
+    # Write the updated content back to the file
+    with open(shell_config, "w") as f:
+        f.writelines(new_lines)
+
+    print(f'Removed {var_name} from {shell_config}.')
+    print(f'Restart your shell or run: source {shell_config}')
+
+
 def calculate_mean_dependency_distance(spacy_doc):
     """
     Calculate the mean dependency distance for tokens in a spaCy Doc object.

{pgsfile-0.5.5/src → pgsfile-0.5.7}/PgsFile/__init__.py

@@ -29,8 +29,8 @@ from .PgsFile import source_path, next_folder_names, get_directory_tree_with_met
 from .PgsFile import remove_empty_folders, remove_empty_txts, remove_empty_lines, remove_empty_last_line
 from .PgsFile import move_file, copy_file, remove_file
 from .PgsFile import concatenate_excel_files
-from .PgsFile import set_permanent_environment_variable
-from .PgsFile import delete_permanent_environment_variable
+from .PgsFile import set_permanent_env_var_win, set_permanent_env_var_mac
+from .PgsFile import delete_permanent_env_var_win, delete_permanent_env_var_mac
 from .PgsFile import get_env_variable, get_all_env_variables
 from .PgsFile import get_system_info
 from .PgsFile import csv_to_json_append

{pgsfile-0.5.5 → pgsfile-0.5.7/PgsFile.egg-info}/PKG-INFO

@@ -1,32 +1,11 @@
 Metadata-Version: 2.4
 Name: PgsFile
-Version: 0.5.5
+Version: 0.5.7
 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
+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
@@ -45,7 +24,17 @@ Requires-Dist: pysbd
 Requires-Dist: nlpir-python
 Requires-Dist: pillow
 Requires-Dist: liwc
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
 Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 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.