sharedkernel 1.7.3__tar.gz → 1.9.0__tar.gz

{sharedkernel-1.7.3 → sharedkernel-1.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sharedkernel
-Version: 1.7.3
+Version: 1.9.0
 Summary: sharekernel is a shared package between all python projects
 Author: Smilinno
 Description-Content-Type: text/markdown
@@ -15,11 +15,19 @@ Requires-Dist: sentry-sdk
 Requires-Dist: jdatetime
 Requires-Dist: persiantools
 Requires-Dist: boto3
+Requires-Dist: python-docx
+Requires-Dist: mammoth
+Requires-Dist: markdown
+Requires-Dist: beautifulsoup4
 
 # SharedKernel
 this a shared kernel package
 
 # Change Log
+### Version 1.9.0
+- Implement DataFormatConverter
+### Version 1.8.0
+- Implement persian number normalizer
 ### Version 1.7.3
 - Add optional folder name for s3 uploader to save the file in
 ### Version 1.7.2

{sharedkernel-1.7.3 → sharedkernel-1.9.0}/README.md

@@ -2,6 +2,10 @@
 this a shared kernel package
 
 # Change Log
+### Version 1.9.0
+- Implement DataFormatConverter
+### Version 1.8.0
+- Implement persian number normalizer
 ### Version 1.7.3
 - Add optional folder name for s3 uploader to save the file in
 ### Version 1.7.2

{sharedkernel-1.7.3 → sharedkernel-1.9.0}/setup.py

@@ -32,10 +32,14 @@ setup(
         "sentry-sdk",
         "jdatetime",
         "persiantools",
-        "boto3"
+        "boto3",
+        "python-docx",
+        "mammoth",
+        "markdown",
+        "beautifulsoup4"
     ],
     # *strongly* suggested for sharing
-    version="1.7.3",
+    version="1.9.0",
     description="sharekernel is a shared package between all python projects",
     long_description=long_description,
     long_description_content_type="text/markdown",

sharedkernel-1.9.0/sharedkernel/data_format_converter.py

@@ -0,0 +1,108 @@
+from abc import ABC, abstractmethod
+import markdown
+
+from docx import Document
+from docx.enum.text import WD_ALIGN_PARAGRAPH
+from docx.oxml.ns import qn
+from docx.oxml import OxmlElement
+from bs4 import BeautifulSoup, NavigableString
+import mammoth
+
+
+class DataFormatConverter(ABC):
+    @abstractmethod
+    def convert(input_path, output_path):
+        pass
+
+    def _get_out_title(self, title: str, file_format: str = ".docx") -> str:
+        return ".".join(title.split(".")[:-1]) + file_format
+
+
+class Md2Docx(DataFormatConverter):
+
+    def __add_hyperlink(self, paragraph, url, text, color="0000FF", underline=True):
+        r_id = paragraph.part.relate_to(url, "hyperlink", is_external=True)
+        hyperlink = OxmlElement("w:hyperlink")
+        hyperlink.set(qn("r:id"), r_id)
+
+        new_run, rPr = OxmlElement("w:r"), OxmlElement("w:rPr")
+        if color:
+            color_element = OxmlElement("w:color")
+            color_element.set(qn("w:val"), color)
+            rPr.append(color_element)
+        if underline:
+            u = OxmlElement("w:u")
+            u.set(qn("w:val"), "single")
+            rPr.append(u)
+        new_run.append(rPr)
+
+        text_elem = OxmlElement("w:t")
+        text_elem.text = text
+        new_run.append(text_elem)
+        hyperlink.append(new_run)
+        paragraph._p.append(hyperlink)
+
+    def __set_right_to_left(self, paragraph):
+        paragraph.alignment = WD_ALIGN_PARAGRAPH.RIGHT
+        paragraph.paragraph_format.right_to_left = True
+
+    @staticmethod
+    def convert(input_path, output_path=None):
+        md2docx = Md2Docx()
+
+        with open(input_path, "r", encoding="utf-8") as f:
+            md_content = f.read()
+
+        output_file = output_path or md2docx._get_out_title(input_path)
+
+        html_content = markdown.markdown(md_content)
+        soup = BeautifulSoup(html_content, "html.parser")
+        doc = Document()
+
+        for element in soup:
+            if element.name == "h1":
+                paragraph = doc.add_paragraph(element.get_text(), style="Heading 1")
+            elif element.name == "h2":
+                paragraph = doc.add_paragraph(element.get_text(), style="Heading 2")
+            elif element.name == "p":
+                paragraph = doc.add_paragraph()
+                for part in element.contents:
+                    if isinstance(part, NavigableString):
+                        paragraph.add_run(str(part))
+                    elif part.name == "a":
+                        md2docx.__add_hyperlink(
+                            paragraph, part["href"], part.get_text()
+                        )
+                    elif part.name == "img":
+                        md2docx.__add_hyperlink(
+                            paragraph, part["src"], part.get("alt", "Image")
+                        )
+            md2docx.__set_right_to_left(paragraph)
+
+        doc.save(output_file)
+        return output_file
+
+
+class Docx2Md(DataFormatConverter):
+    def _get_out_title(self, title: str, file_format: str = ".txt") -> str:
+        return super()._get_out_title(title, file_format)
+
+    @staticmethod
+    def convert(input_path: str, output_path: str = None):
+        docx2md = Docx2Md()
+        with open(input_path, "rb") as docx:
+            result = mammoth.convert_to_markdown(
+                docx,
+                convert_image=mammoth.images.img_element(
+                    lambda image: {"src": "images/" + image.content_type.split("/")[-1]}
+                ),
+            )
+
+        output_path = output_path or docx2md._get_out_title(input_path)
+
+        with open(output_path, "w", encoding="utf-8") as md_file:
+            md_file.write(result.value)
+
+        if result.messages:
+            for message in result.messages:
+                print("Warning:", message)

sharedkernel-1.9.0/sharedkernel/normalizer/__init__.py

@@ -0,0 +1,2 @@
+from .phone_number_normalizer import PhoneNumberNormalizer
+from .number_normalizer import NumberNormalizer

sharedkernel-1.9.0/sharedkernel/normalizer/number_normalizer.py

@@ -0,0 +1,8 @@
+class NumberNormalizer:
+    @staticmethod
+    def persian_number(text):
+        persian_numbers = "۰۱۲۳۴۵۶۷۸۹"
+        english_numbers = "0123456789"
+        translation_table = str.maketrans(persian_numbers, english_numbers)
+        return text.translate(translation_table)
+

{sharedkernel-1.7.3 → sharedkernel-1.9.0}/sharedkernel/s3_uploader.py

@@ -51,7 +51,6 @@ class S3Uploader:
 
         # Upload the file object
         self.s3.upload_fileobj(file_obj, self.bucket, object_name, ExtraArgs={'ACL':'public-read'})
-        print(f"File object uploaded to {self.bucket} as {object_name}.")
 
         # Construct the URL of the uploaded file
         file_url = f"{self.endpoint_url}/{self.bucket}/{object_name}"

{sharedkernel-1.7.3 → sharedkernel-1.9.0}/sharedkernel.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sharedkernel
-Version: 1.7.3
+Version: 1.9.0
 Summary: sharekernel is a shared package between all python projects
 Author: Smilinno
 Description-Content-Type: text/markdown
@@ -15,11 +15,19 @@ Requires-Dist: sentry-sdk
 Requires-Dist: jdatetime
 Requires-Dist: persiantools
 Requires-Dist: boto3
+Requires-Dist: python-docx
+Requires-Dist: mammoth
+Requires-Dist: markdown
+Requires-Dist: beautifulsoup4
 
 # SharedKernel
 this a shared kernel package
 
 # Change Log
+### Version 1.9.0
+- Implement DataFormatConverter
+### Version 1.8.0
+- Implement persian number normalizer
 ### Version 1.7.3
 - Add optional folder name for s3 uploader to save the file in
 ### Version 1.7.2

{sharedkernel-1.7.3 → sharedkernel-1.9.0}/sharedkernel.egg-info/SOURCES.txt

@@ -1,6 +1,7 @@
 README.md
 setup.py
 sharedkernel/common.py
+sharedkernel/data_format_converter.py
 sharedkernel/date_converter.py
 sharedkernel/jwt_service.py
 sharedkernel/regex_masking.py
@@ -24,6 +25,7 @@ sharedkernel/exception/__init__.py
 sharedkernel/exception/exception.py
 sharedkernel/exception/exception_handlers.py
 sharedkernel/normalizer/__init__.py
+sharedkernel/normalizer/number_normalizer.py
 sharedkernel/normalizer/phone_number_normalizer.py
 sharedkernel/objects/__init__.py
 sharedkernel/objects/base_document.py

{sharedkernel-1.7.3 → sharedkernel-1.9.0}/sharedkernel.egg-info/requires.txt

@@ -9,3 +9,7 @@ sentry-sdk
 jdatetime
 persiantools
 boto3
+python-docx
+mammoth
+markdown
+beautifulsoup4

sharedkernel-1.7.3/sharedkernel/normalizer/__init__.py

@@ -1 +0,0 @@
-from .phone_number_normalizer import PhoneNumberNormalizer