label-sorter 0.1__tar.gz

label_sorter-0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Harilal Sunil
+
+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.

label_sorter-0.1/PKG-INFO

@@ -0,0 +1,58 @@
+Metadata-Version: 2.4
+Name: label_sorter
+Version: 0.1
+Summary: Library to sort Amazon and Shopify shipping labels
+Home-page: https://github.com/harilal766/Ecommerce-label-sorter
+Author: Harry19967
+Author-email: harilalsunil2@gmail.com
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-python
+Dynamic: summary
+
+# Ecom-label-sorter
+
+## Description:
+1. A python program to sort Amazon and Shopify pdf shipping labels.
+2. Each sorted group of orders will be stored in a dedicated pdf file which is named after the product name and quantity.
+3.  On Miscellaneous orders these pdf file will be named "Mixed".
+4. All of these files will be stored inside a folder which is named after the input pdf file.
+
+## Reason to develop this project
+Manually sorting a large PDF containing multiple orders is time-consuming and prone to human error.
+
+# Installation
+```
+pip install ecom_label_sorter
+```
+
+# Usage
+```
+from label_sorter import Label_sorter
+
+sorter_instance = Label(pdf_path = <path to the pdf file>)
+
+# Creating sorted pdf files
+# this will create a folder named after the pdf file and will be containig sorted pdf files and summary json fle.
+sorter_instance.created_sorted_pdf_files()
+
+```
+
+
+
+
+# Classes and their descriptions
+
+[ Label Sorter](docs/Label_Sorter.md)

label_sorter-0.1/README.md

@@ -0,0 +1,34 @@
+# Ecom-label-sorter
+
+## Description:
+1. A python program to sort Amazon and Shopify pdf shipping labels.
+2. Each sorted group of orders will be stored in a dedicated pdf file which is named after the product name and quantity.
+3.  On Miscellaneous orders these pdf file will be named "Mixed".
+4. All of these files will be stored inside a folder which is named after the input pdf file.
+
+## Reason to develop this project
+Manually sorting a large PDF containing multiple orders is time-consuming and prone to human error.
+
+# Installation
+```
+pip install ecom_label_sorter
+```
+
+# Usage
+```
+from label_sorter import Label_sorter
+
+sorter_instance = Label(pdf_path = <path to the pdf file>)
+
+# Creating sorted pdf files
+# this will create a folder named after the pdf file and will be containig sorted pdf files and summary json fle.
+sorter_instance.created_sorted_pdf_files()
+
+```
+
+
+
+
+# Classes and their descriptions
+
+[ Label Sorter](docs/Label_Sorter.md)

label_sorter-0.1/label_sorter/__init__.py

@@ -0,0 +1 @@
+from .core import LabelSorter

label_sorter-0.1/label_sorter/core.py

@@ -0,0 +1,162 @@
+import pdfplumber, re, os,sys, logging, json
+from pypdf import PdfReader, PdfWriter
+from pprint import pprint
+from label_sorter.platforms.ecommerce.base_label import BaseLabel
+from label_sorter.platforms.ecommerce.shopify import ShopifyLabel
+from label_sorter.platforms.ecommerce.amazon import AmazonLabel
+
+logging.getLogger('pdfminer').setLevel(logging.ERROR)
+
+class LabelSorter:
+    def __init__(self, pdf_path):
+        self.sorted_dict = {}
+        self.label_filepath = pdf_path
+        self.output_folder = self.label_filepath.replace(".pdf","")
+        self.platform = self.find_platform()
+        
+    def find_platform(self) -> str:
+        platform = None
+        try:
+            with pdfplumber.open(self.label_filepath) as pdf_file:
+                total_pages = 0; amazon_count = 0 
+                
+                shopify_order_id_count, amazon_order_id_count = 0, 0
+                
+                for page_index, page in enumerate(pdf_file.pages):
+                    total_pages += 1
+                    page_text = page.extract_text(); page_tables = page.extract_tables()
+                    
+                    # Shopify Initializations
+                    sh = ShopifyLabel(page_text=page_text, page_table=page_tables,page_num=0)
+                    am = AmazonLabel(page_text=page_text, page_table=page_tables,page_num=0)
+                    
+                    if re.findall(sh.shopify_order_id_pattern, page_text):
+                        shopify_order_id_count += 1
+                    elif re.findall(am.amazon_order_id_pattern, page_text):
+                        amazon_order_id_count += 1
+                        
+                if total_pages == shopify_order_id_count:
+                    platform = "Shopify"
+                # this condition is not complete, need to add overlap page detection
+                elif amazon_order_id_count > 0:
+                    platform = "Amazon"
+            
+        except FileNotFoundError:
+            print(f"The file {self.label_filepath} does not exist.")
+        except Exception as e:
+            print(e)
+        else:
+            return platform
+        
+    def create_sorted_summary(self):
+        if not self.platform:
+            sys.exit("Unsupported Platform, exiting....")
+        page_debrief = None
+        try:
+            print(f"Platform : {self.platform}")
+            with pdfplumber.open(self.label_filepath) as pdf_file:
+                for page_index, page in enumerate(pdf_file.pages):
+                    page_text = page.extract_text(); page_table = page.extract_tables()
+                    page_number = page_index+1
+                    
+                    #Label_instance = BaseLabel(page_text=page_text, page_table=page_table,page_num=page_number)
+                    debriefs = {
+                        "Shopify" : ShopifyLabel(page_text=page_text, page_table=page_table,page_num=page_number).analyze_shpy_page(),
+                        "Amazon" : AmazonLabel(page_text=page_text, page_table=page_table,page_num=page_number).analyze_amzn_page(),
+                    }
+                    
+                    page_debrief = debriefs[self.platform]
+                    
+                    print(f"{page_number} : {page_debrief}")
+                    
+                    is_page_debrief_populated = page_debrief["order_id"] != None
+                    # sorting summary
+                    if self.platform and is_page_debrief_populated:
+                        self.populate_shipment_summary(
+                            sorting_key=page_debrief["sorting_key"], qty=page_debrief["qty"],
+                            page_nums=[page_number - 1, page_number] if self.platform == "Amazon" else [page_number]
+                        )
+                    
+        except FileNotFoundError as fe:
+            print(fe)
+        except Exception as e:
+            print(e)
+        else:
+            return self.sorted_dict
+        
+    def populate_shipment_summary(self, sorting_key:str, page_nums:list, qty : str) -> None:
+        try:
+            # different conditions for mixed and single items
+            # sorting key initialization
+            numbers_list = None
+            # Adding sorting key if not present
+            if sorting_key not in self.sorted_dict.keys(): 
+                self.sorted_dict[sorting_key] = [] if sorting_key == "Mixed" else {}
+
+            if sorting_key == "Mixed":
+                numbers_list = self.sorted_dict[sorting_key]
+            else:
+                if qty not in self.sorted_dict[sorting_key].keys():
+                    self.sorted_dict[sorting_key][qty] = []
+                numbers_list = self.sorted_dict[sorting_key][qty]
+            numbers_list += page_nums
+            
+        except Exception as e:
+            print(e)
+            
+    def create_single_pdf_file(self, pdf_name, page_numbers):
+        try:
+            reader = PdfReader(self.label_filepath); writer = PdfWriter()
+            print(pdf_name, page_numbers)
+            # adding pages to the writer
+            for page in page_numbers:
+                writer.add_page(reader.pages[page-1])
+                
+            page_count = len(page_numbers)
+            order_count = int(page_count/2) if self.platform == "Amazon" else page_count
+            
+            sorted_pdf_file = f"{re.sub(r"[\|\.]*",r"",pdf_name)} - {order_count} order{"s" if order_count > 1 else ""}.pdf"
+        except Exception as e:
+            print(e)
+        else:
+            if writer:
+                if sorted_pdf_file:
+                    out_filepath = os.path.join(self.output_folder, sorted_pdf_file)
+                    with open(out_filepath, "wb") as out_pdf:
+                        writer.write(out_pdf)        
+            
+    def create_sorted_pdf_files(self):
+        summary_dict = self.create_sorted_summary()
+        
+        #pprint(summary_dict.keys())
+        
+        if len(summary_dict.keys()) == 0:
+            sys.exit("Cannot sort with empty summary...")
+            
+        order_count = None; page_numbers = None
+        output_file = None 
+        
+        # Create output folder if not created already.
+        if not os.path.exists(self.output_folder):
+            os.makedirs(self.output_folder)
+            print(f"Created output folder : {self.output_folder}")
+        
+        # save the summary as a json file to the output folder
+        with open(f"{self.output_folder}/summary.json","w") as summary_json:
+            json.dump(summary_dict, summary_json)
+            
+        try:
+            print(f"Sorted Summary :")
+            for sorting_key, value in summary_dict.items():
+                # Assigning output file name and its pages according to order type
+                # Mixed orders
+                if type(value) == list:
+                    self.create_single_pdf_file(pdf_name=sorting_key, page_numbers=value)
+                # single item orders
+                elif type(value) == dict:
+                    #print(f"Writing Single item order",end=", ")
+                    for qty,page_list in value.items():
+                        #print(f"Detected more than one qty.")
+                        self.create_single_pdf_file(pdf_name=f"{sorting_key} - {qty}", page_numbers=page_list)
+        except Exception as e:
+            print(f"Err : {e}")

label_sorter-0.1/label_sorter.egg-info/PKG-INFO

@@ -0,0 +1,58 @@
+Metadata-Version: 2.4
+Name: label_sorter
+Version: 0.1
+Summary: Library to sort Amazon and Shopify shipping labels
+Home-page: https://github.com/harilal766/Ecommerce-label-sorter
+Author: Harry19967
+Author-email: harilalsunil2@gmail.com
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-python
+Dynamic: summary
+
+# Ecom-label-sorter
+
+## Description:
+1. A python program to sort Amazon and Shopify pdf shipping labels.
+2. Each sorted group of orders will be stored in a dedicated pdf file which is named after the product name and quantity.
+3.  On Miscellaneous orders these pdf file will be named "Mixed".
+4. All of these files will be stored inside a folder which is named after the input pdf file.
+
+## Reason to develop this project
+Manually sorting a large PDF containing multiple orders is time-consuming and prone to human error.
+
+# Installation
+```
+pip install ecom_label_sorter
+```
+
+# Usage
+```
+from label_sorter import Label_sorter
+
+sorter_instance = Label(pdf_path = <path to the pdf file>)
+
+# Creating sorted pdf files
+# this will create a folder named after the pdf file and will be containig sorted pdf files and summary json fle.
+sorter_instance.created_sorted_pdf_files()
+
+```
+
+
+
+
+# Classes and their descriptions
+
+[ Label Sorter](docs/Label_Sorter.md)

label_sorter-0.1/label_sorter.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+LICENSE
+README.md
+pyproject.toml
+setup.py
+label_sorter/__init__.py
+label_sorter/core.py
+label_sorter.egg-info/PKG-INFO
+label_sorter.egg-info/SOURCES.txt
+label_sorter.egg-info/dependency_links.txt
+label_sorter.egg-info/top_level.txt
+tests/test_core.py

label_sorter-0.1/label_sorter.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

label_sorter-0.1/label_sorter.egg-info/top_level.txt

@@ -0,0 +1 @@
+label_sorter

label_sorter-0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

label_sorter-0.1/setup.py

@@ -0,0 +1,26 @@
+from setuptools import setup, find_packages
+from pathlib import Path
+
+this_directory = Path(__file__).parent
+long_description = (this_directory / "README.md").read_text()
+
+setup(
+    name="label_sorter",
+    version="0.1",
+    packages=["label_sorter"],
+    install_requires = [
+        
+    ],
+    author = "Harry19967",
+    author_email="harilalsunil2@gmail.com",
+    description = "Library to sort Amazon and Shopify shipping labels",
+    url= "https://github.com/harilal766/Ecommerce-label-sorter",
+    license = "MIT",
+    classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent"
+    ],
+    python_requires = ">=3.9",
+    long_description=long_description,
+    long_description_content_type='text/markdown'
+)

label_sorter-0.1/tests/test_core.py

@@ -0,0 +1,26 @@
+import sys, os, pytest
+
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+from filepaths import amazon_pdf, shopify_pdf
+from label_sorter.core import LabelSorter
+
+class Test_LabelSorter:
+    label_inst = LabelSorter(pdf_path=shopify_pdf)
+    
+    files = {
+        "Shopify" : shopify_pdf,
+        "Amazon" : amazon_pdf
+    }
+    
+    def test_find_platfrom(self):
+        for key,value in self.files.items():
+            inst = LabelSorter(pdf_path=value)
+            assert inst.find_platform() == key
+        
+    def test_sort_label(self):
+        assert len(self.label_inst.create_sorted_summary().keys()) > 0
+        
+        
+    # need more tests for mixed orders and amazon qr page
+