PgsFile 0.4.1__py3-none-any.whl → 0.4.2__py3-none-any.whl

PgsFile/PgsFile.py

@@ -4000,4 +4000,30 @@ def resize_image(input_image_path, output_image_path, max_size_kb):
         if size <= max_size_kb:
             print(f"Image resized successfully to {size} KB.")
         else:
-            print("Could not reduce the image size below 2MB.")
+            print("Could not reduce the image size below 2MB.")
+
+import base64
+def convert_image_to_url(image_path: str) -> str:
+    """
+    Convert an image file to a base64 encoded URL format.
+
+    :param image_path: Path to the image file.
+    :return: A string representing the image in the required URL format.
+    """
+    # Check if the file exists
+    if not os.path.isfile(image_path):
+        raise FileNotFoundError(f"The file {image_path} does not exist.")
+
+    # Open and read the image file in binary mode
+    with open(image_path, "rb") as f:
+        image_data = f.read()
+
+    # Extract the file extension and convert it to base64
+    file_extension = os.path.splitext(image_path)[1][1:]
+    base64_image_data = base64.b64encode(image_data).decode('utf-8')
+
+    # Create the image URL
+    image_url = f"data:image/{file_extension};base64,{base64_image_data}"
+
+    return image_url
+

PgsFile/__init__.py

@@ -64,5 +64,6 @@ from .PgsFile import timeit
 from .PgsFile import replace_white_with_transparency
 from .PgsFile import simhei_default_font_path_MacOS_Windows
 from .PgsFile import get_font_path, resize_image
+from .PgsFile import convert_image_to_url
 
 name = "PgsFile"

PgsFile/models/prompts/4. OCR prompt.txt

@@ -0,0 +1 @@
+Perform OCR on the image and return all the extracted text, including both running paragraphs and tables, without any additional explanation. Ensure that tables are kept in their raw format as accurately as possible, without any content or arrangement changes.

{PgsFile-0.4.1.dist-info → PgsFile-0.4.2.dist-info}/METADATA

@@ -1,8 +1,8 @@
 Metadata-Version: 2.1
 Name: PgsFile
-Version: 0.4.1
-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 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
+Version: 0.4.2
+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, 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/lWMkYDWQMjBJNKY2vMYTpw
 Author: Pan Guisheng
 Author-email: 895284504@qq.com
 License: Educational free
@@ -34,7 +34,7 @@ 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, keywords extraction, MDD, WSD, LIWC, and MIP analysis using prepared LLM prompts.
+7. **NLP:** Perform OCR, 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, resize images) and manage fonts for rendering text.
 

{PgsFile-0.4.1.dist-info → PgsFile-0.4.2.dist-info}/RECORD

@@ -1,5 +1,5 @@
-PgsFile/PgsFile.py,sha256=yGDHyK4Mq8dCPZRl9KJv9HlKGxTUA1hgprPwAubdwy4,164722
-PgsFile/__init__.py,sha256=xCXOhl0tkHYk5ZuL8VbaONiXt9A9o25hOgwx8XQLY9w,3510
+PgsFile/PgsFile.py,sha256=piiVyMNNZoXLSuxbcg-5wXJYUgnEAirQUs4GEq7Neaw,165583
+PgsFile/__init__.py,sha256=Qg7xt9wR83ySrS8z0Fy6xn5JttDLoEPLIhpnj7sWGdc,3553
 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
@@ -2571,7 +2571,7 @@ PgsFile/Corpora/Stopwords/turkish.txt,sha256=uGUvjEm2GR8PuVY_JeHNxhD7cWlNlF7vc3V
 PgsFile/Corpora/Stopwords/ukrainian.txt,sha256=fEzWLTwnWJriILkO-5jSfE2SpqY-GPf_kR4zid3MFUI,4131
 PgsFile/Corpora/Stopwords/vietnamese.txt,sha256=88yRtVMaRSFqas1iGGa6kOGDCZTgtzRPmR3q9dHshdc,20485
 PgsFile/Corpora/Terminology/Chinese_Thought.json,sha256=CdkuF2wLaDC5V3sRefcU1RZwXm4-wTZ-Qfk8r7gsu8I,2301866
-PgsFile/models/NLPIR.user,sha256=DykLJdr8_cVHrdCnDJES1O5dgmnYqfaSO1_dtAVKYJk,3356
+PgsFile/models/NLPIR.user,sha256=jLOqi6EhYj9p7eGcTWECcmElwsvNWaUBTSkMeBsO_S4,3356
 PgsFile/models/model_reviews2.2.bin,sha256=D6uL8KZIxD0rfWjH0kYEb7z_HE4aTJXpj82HzsCOpuk,1943196
 PgsFile/models/model_reviews_ReadMe.txt,sha256=Q9uLJwudMmsTKfd11l1tOcIP8lwsemIwnAVJG_3SYjU,11433
 PgsFile/models/dics/BNC_COCA_lists.xlsx,sha256=ua5iQzEf5UQpsCezbsliNF6e_PYHIHGSJUjn9MyEEks,1229313
@@ -2587,8 +2587,9 @@ PgsFile/models/fonts/陆柬之行书字体.ttf,sha256=Zpd4Z7E9w-Qy74yklXHk4vM7HO
 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-0.4.1.dist-info/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
-PgsFile-0.4.1.dist-info/METADATA,sha256=yaW5a8anEhCTX5J1BF_U53hKIAl0z31-03k9d3Tio2Y,2985
-PgsFile-0.4.1.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-PgsFile-0.4.1.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
-PgsFile-0.4.1.dist-info/RECORD,,
+PgsFile/models/prompts/4. OCR prompt.txt,sha256=YxUQ2IlE52k0fcBnGsuOHqWAmfiEmIu6iRz5zecQ8dk,260
+PgsFile-0.4.2.dist-info/LICENSE,sha256=cE5c-QToSkG1KTUsU8drQXz1vG0EbJWuU4ybHTRb5SE,1138
+PgsFile-0.4.2.dist-info/METADATA,sha256=ETpekk4cnT1bC3ZCTlCT7U7mldyOUNO1AW73-L1CUZw,2967
+PgsFile-0.4.2.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+PgsFile-0.4.2.dist-info/top_level.txt,sha256=028hCfwhF3UpfD6X0rwtWpXI1RKSTeZ1ALwagWaSmX8,8
+PgsFile-0.4.2.dist-info/RECORD,,