PgsFile 0.5.6__py3-none-any.whl → 0.5.8__py3-none-any.whl

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):

PgsFile/models/prompts/6. ATE3 prompt.txt

@@ -3,8 +3,8 @@ Extract terms from the input text and classify each term into one of the followi
 •	Common_Term: Domain-specific but not lexicon-specific (known by laypersons, still relevant to the domain)
 •	OOD_Term: Lexicon-specific but not domain-specific (known mainly by experts, but not relevant to the domain)
 
-Terms should not include named entities.
-Output Format (a list of python-list): [["2-vessel cad", "Specific_Term"], ["aortic valve", "Common_Term"], ["p-value", "OOD_Term"]]
+Terms offered should not include named entities.
+Return Output Format (a list of python-list): [["2-vessel cad", "Specific_Term"], ["aortic valve", "Common_Term"], ["p-value", "OOD_Term"]]
 If no terms are presented, keep it an empty list: []
 Do not include any explanations or additional text in the output.
 
@@ -13,7 +13,5 @@ Examples (in the domain of heart failure):
 •	"heart" → "Common_Term": relevant to the domain and understandable by the general public.
 •	"p-value" → "OOD_Term": expert-level term, but not domain-specific to heart failure.
 
-Now, please extract the terms from the following sentence:
-
-Sentence: "{sentence}"
-Output: [[]]
+Now, please extract the terms from the following sentence: "{sentence}"
+Output: [["list of terms present"]]

{pgsfile-0.5.6.dist-info → pgsfile-0.5.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PgsFile
-Version: 0.5.6
+Version: 0.5.8
 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.
 Home-page: https://github.com/Petercusin/PgsFile
 Author: Pan Guisheng

{pgsfile-0.5.6.dist-info → pgsfile-0.5.8.dist-info}/RECORD

@@ -1,4 +1,4 @@
-PgsFile/PgsFile.py,sha256=OGbj8eYkXdAyWs2Or7TtHYrBgCiaeT1wwxcNUvLMUnA,180569
+PgsFile/PgsFile.py,sha256=BiXU3odbUt8m9nq8yCT662l8tzM3W--drzLcyYacjCc,180591
 PgsFile/__init__.py,sha256=4AMmYVzDAr2Zy1r8WuN32lqgCxPaERTu5g6lnax4B9o,3840
 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
@@ -2592,12 +2592,12 @@ PgsFile/models/prompts/2. WSD prompt.txt,sha256=o-ZFtCRUCDrXgm040WTQch9v2Y_r2SIl
 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/6. ATE3 prompt.txt,sha256=xn5HRkzIkrbdUP2I-huTd0KpuiQdRYFZZO02yJiOguM,1279
 PgsFile/models/prompts/7. SentAlign prompt.txt,sha256=hXpqqC-CAgo8EytkJ0MaLhevLefALazWriY-ew39jxs,1537
 PgsFile/models/prompts/8. TitleCase prompt.txt,sha256=4p-LfGy0xAj2uPi9amyMm41T6Z17VNpFFsGZOgWhROs,1136
 PgsFile/models/prompts/9. TextClassification prompt.txt,sha256=JhQJu3rQSstNtkIkxPR1K-QmH9sGBEhbVKHAi7ItMUA,1066
-pgsfile-0.5.6.dist-info/licenses/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
-pgsfile-0.5.6.dist-info/METADATA,sha256=mpdG5cKeYpf0jkEc0yKcRi-j_pLnL2s_52skr0SI2u0,3399
-pgsfile-0.5.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-pgsfile-0.5.6.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
-pgsfile-0.5.6.dist-info/RECORD,,
+pgsfile-0.5.8.dist-info/licenses/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
+pgsfile-0.5.8.dist-info/METADATA,sha256=a3zd1hCPn2eQv49UsxmCPDpg6ADBVnl4sNCzfcd-Ba0,3399
+pgsfile-0.5.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+pgsfile-0.5.8.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
+pgsfile-0.5.8.dist-info/RECORD,,