PgsFile 0.3.9__py3-none-any.whl → 0.4.0__py3-none-any.whl

PgsFile/PgsFile.py

@@ -3819,7 +3819,7 @@ def calculate_log_likelihood(target_count, reference_count, total_target, total_
 def extract_keywords_en(target_text, top_n=10):
     """Extract keywords from target text using log-likelihood with absolute reference frequencies."""
     # Example usage
-    my_dic_path = get_library_location("PgsFile")+"/PgsFile/models/dics/unigram_freq_only.json"
+    my_dic_path = get_library_location("PgsFile")+"/PgsFile/models/dics/unigram_freq_only.json" # BNC_wordlist
     reference_freq = get_data_json(my_dic_path)
     # Tokenize target text and preserve original case
     original_words = word_tokenize2(target_text)
@@ -3852,3 +3852,52 @@ def extract_keywords_en(target_text, top_n=10):
 
     # Return top N keywords
     return keyword_scores[:top_n]
+
+def resize_image(input_image_path, output_image_path, max_size_kb):
+    '''
+    # Example 1: Resizing a JPG image
+    input_image_path_jpg = 'example_input.jpg'
+    output_image_path_jpg = 'example_output_resized.jpg'
+    resize_image(input_image_path_jpg, output_image_path_jpg, max_size_kb=2048)
+
+    # Example 2: Resizing a PNG image
+    input_image_path_png = 'example_input.png'
+    output_image_path_png = 'example_output_resized.png'
+    resize_image(input_image_path_png, output_image_path_png, max_size_kb=2048)
+    '''
+    # Open the image file
+    with Image.open(input_image_path) as img:
+        # Function to save the image and check its size
+        def save_image(img, output_path, quality=95):
+            if output_path.lower().endswith('.jpg'):
+                img.save(output_path, 'JPEG', quality=quality)
+            else:
+                img.save(output_path, 'PNG', optimize=True)
+
+        # Initial save to check the size
+        save_image(img, output_image_path)
+
+        # Check the size and reduce quality/dimensions if necessary
+        size = os.path.getsize(output_image_path) // 1024  # Size in KB
+
+        # Reduce quality for JPG or optimize PNG
+        quality = 95
+        while size > max_size_kb:
+            # Reduce dimensions
+            width, height = img.size
+            img = img.resize((int(width * 0.9), int(height * 0.9)), Image.LANCZOS)
+
+            # Save the image
+            save_image(img, output_image_path, quality)
+            size = os.path.getsize(output_image_path) // 1024
+
+            # Reduce quality for JPG
+            if output_image_path.lower().endswith('.jpg'):
+                quality -= 5
+                if quality < 10:  # Prevent quality from going too low
+                    break
+
+        if size <= max_size_kb:
+            print(f"Image resized successfully to {size} KB.")
+        else:
+            print("Could not reduce the image size below 2MB.")

PgsFile/__init__.py

@@ -63,6 +63,6 @@ from .PgsFile import timeit
 # 9. Visualization
 from .PgsFile import replace_white_with_transparency
 from .PgsFile import simhei_default_font_path_MacOS_Windows
-from .PgsFile import get_font_path
+from .PgsFile import get_font_path, resize_image
 
 name = "PgsFile"

{PgsFile-0.3.9.dist-info → PgsFile-0.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PgsFile
-Version: 0.3.9
+Version: 0.4.0
 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 tokenization, lemmatization, POS tagging, NER, keywords extraction, dependency parsing, MDD, WSD, LIWC, and MIP analysis. 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/12-KVLfaPszoZkCxuRd-nQ?token=1589547443&lang=zh_CN
 Author: Pan Guisheng
@@ -34,9 +34,9 @@ Key Features:
 4. **Data Storage:** Write and append data to text files, Excel, JSON, 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, and prepare data for analysis, utilizing valuable corpora and dictionaries such as CET-4/6 vocabulary and BNC-COCA word lists.
-7. **NLP:** Perform word tokenization, lemmatization, POS tagging, NER, dependency parsing, MDD, WSD, LIWC, and MIP analysis using prepared LLM prompts.
+7. **NLP:** Perform word tokenization, lemmatization, POS tagging, NER, dependency parsing, keywords extraction, MDD, WSD, LIWC, and MIP analysis 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) and manage fonts for rendering text.
+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

{PgsFile-0.3.9.dist-info → PgsFile-0.4.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-PgsFile/PgsFile.py,sha256=JtoRVZv3xeTBtlHZ1oXHCjnSlZP22ZvxDuLr5AprCHY,159856
-PgsFile/__init__.py,sha256=cqfmNpluuCBtTLEldYPZ9KtuCtlYqsytc38BvY5R49o,3486
+PgsFile/PgsFile.py,sha256=Ko2HpUkWdNM8vAQy9wCkbFNDMuAQ2fQCCQy-IEeBWy4,161852
+PgsFile/__init__.py,sha256=nsKnjOskNjAsmtC88W62ARm5k9OGAqpo7_si66Mw0nM,3500
 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
@@ -2586,8 +2586,8 @@ 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-0.3.9.dist-info/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
-PgsFile-0.3.9.dist-info/METADATA,sha256=W4XQbTgzIRhLl9xnWrW4XdBVvwhqi3ZHvtcrJnnMSxo,2949
-PgsFile-0.3.9.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-PgsFile-0.3.9.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
-PgsFile-0.3.9.dist-info/RECORD,,
+PgsFile-0.4.0.dist-info/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
+PgsFile-0.4.0.dist-info/METADATA,sha256=OuxX_yi0yRKRnXyqS-QL5JEBbrbALHjEXvGg2w_gikY,2985
+PgsFile-0.4.0.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+PgsFile-0.4.0.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
+PgsFile-0.4.0.dist-info/RECORD,,