From 85a485f82188750da781e0ae5698fe6756696566 Mon Sep 17 00:00:00 2001
From: Gabriela de Santana Carrara <gabriela.de.santana.carrara@cern.ch>
Date: Fri, 27 Mar 2026 09:00:16 +0100
Subject: [PATCH 1/5] digitization: proposal for refactor PDF check script

Ref: cern-sis/digitization#22
---
 .gitignore                      |   2 +
 refactory/main.py               | 121 ++++++++++++++++++++++++++++++++
 refactory/storage_connection.py | 105 +++++++++++++++++++++++++++
 refactory/test_connections.py   |  81 +++++++++++++++++++++
 refactory/validate_pdf.py       |  34 +++++++++
 5 files changed, 343 insertions(+)
 create mode 100644 refactory/main.py
 create mode 100644 refactory/storage_connection.py
 create mode 100644 refactory/test_connections.py
 create mode 100644 refactory/validate_pdf.py

diff --git a/.gitignore b/.gitignore
index da1cc52..8d48b18 100644
--- a/.gitignore
+++ b/.gitignore
@@ -18,3 +18,5 @@ import_xml_files/
 .venv
 
 
+requirements.txt
+s3_pdf_issues.json
\ No newline at end of file
diff --git a/refactory/main.py b/refactory/main.py
new file mode 100644
index 0000000..5594b77
--- /dev/null
+++ b/refactory/main.py
@@ -0,0 +1,121 @@
+import tempfile
+import re
+import os
+import sys
+import json
+from storage_connection import StorageProvider, S3Provider, CernboxProvider
+from validate_pdf import is_pdf_valid
+
+def run_validation_pipeline(provider: StorageProvider, base_path: str, log_file: str, start: int = None, end: int = None, upload_reports: bool = False):
+    """Navigates directories, validates files, and logs corrupted files."""
+    print(f"Discovering folders in: {base_path}")
+    
+    folders = provider.list_folders(base_path)
+    
+    if not folders:
+        print("No folders found in this path.")
+        return
+
+    found_box_numbers = set()
+    empty_folders = []
+    corrupted_files = []
+    valid_files_count = 0
+
+    print("Starting validation...")
+
+    for folder in folders:
+        if "BOITE_" not in folder:
+            continue
+
+        match = re.search(r"BOITE_O0(\d+)", folder)
+        if match:
+            box_num = int(match.group(1))
+            if start is not None and box_num < start:
+                continue
+            if end is not None and box_num > end:
+                continue
+            
+            found_box_numbers.add(box_num)
+        else:
+            continue
+            
+        print(f"\nChecking folder: {folder}")
+        pdf_files = provider.list_pdfs(folder)
+
+        if not pdf_files:
+            print("   Empty folder or no PDFs.")
+            empty_folders.append(folder)
+            continue
+
+        for file_path in pdf_files:
+            print(f"   {file_path.split('/')[-1]} ... ", end="")
+            
+            with tempfile.NamedTemporaryFile(delete=True) as tmp:
+                provider.download_to_temp(file_path, tmp.name)
+                valid = is_pdf_valid(tmp.name)
+            
+            if valid:
+                print("✅ Valid")
+                valid_files_count += 1
+            else:
+                print("❌ Corrupted")
+                corrupted_files.append(file_path)
+
+    with open(log_file, "w", encoding="utf-8") as log:
+        for cf in corrupted_files:
+            log.write(f"Corrupted PDF: {cf}\n")
+
+    missing_boxes = []
+    if start is not None and end is not None:
+        expected_boxes = set(range(start, end + 1))
+        missing_boxes = sorted(list(expected_boxes - found_box_numbers))
+
+    json_report = {
+        "metadata": {
+            "base_path": base_path,
+            "range_analyzed": {"start": start, "end": end}
+        },
+        "statistics": {
+            "valid_files": valid_files_count,
+            "corrupted_files_count": len(corrupted_files),
+            "empty_folders_count": len(empty_folders),
+            "missing_boxes_count": len(missing_boxes) if missing_boxes else 0
+        },
+        "issues": {
+            "missing_boxes": missing_boxes if missing_boxes else [],
+            "empty_folders": empty_folders,
+            "corrupted_files": corrupted_files
+        }
+    }
+
+    json_file_path = log_file.replace(".log", ".json")
+    with open(json_file_path, "w", encoding="utf-8") as jf:
+        json.dump(json_report, jf, indent=4)
+
+    print(f"\nDone! The text log of corrupted files was saved to: {log_file}")
+    print(f"The structured JSON data was saved to: {json_file_path}")
+
+    if upload_reports:
+        remote_log_path = f"{base_path.rstrip('/')}/{os.path.basename(log_file)}"
+        remote_json_path = f"{base_path.rstrip('/')}/{os.path.basename(json_file_path)}"
+        
+        print(f"Uploading reports back to the cloud ({base_path})...")
+        try:
+            provider.upload_file(log_file, remote_log_path)
+            provider.upload_file(json_file_path, remote_json_path)
+            print(f"✅ Upload successful! Files available at: {remote_log_path} and {remote_json_path}")
+        except Exception as e:
+            print(f"❌ Failed to upload reports: {e}")
+
+if __name__ == "__main__":
+    s3_provider = S3Provider(bucket="digitization-dev")
+    # cernbox_provider = CernboxProvider(public_link_hash="XjjFxUWUMpuTYCz")
+    
+    run_validation_pipeline(
+        provider=s3_provider, #cernbox_provider
+        base_path="cern-archives/raw/PDF/", #"teste/", 
+        log_file="s3_pdf_issues.log",
+        start=int(sys.argv[1]), #123
+        end=int(sys.argv[2]), #126
+        upload_reports=sys.argv[3] # 0 | 1 
+    )
\ No newline at end of file
diff --git a/refactory/storage_connection.py b/refactory/storage_connection.py
new file mode 100644
index 0000000..7f0bc94
--- /dev/null
+++ b/refactory/storage_connection.py
@@ -0,0 +1,105 @@
+import boto3
+import requests
+import xml.etree.ElementTree as ET
+from abc import ABC, abstractmethod
+import os
+
+class StorageProvider(ABC):
+    """Base interface for storage providers."""
+    @abstractmethod
+    def list_folders(self, base_path: str) -> list[str]:
+        pass
+
+    @abstractmethod
+    def list_pdfs(self, folder_path: str) -> list[str]:
+        pass
+
+    @abstractmethod
+    def download_to_temp(self, file_path: str, temp_file_path: str) -> None:
+        pass
+        
+    @abstractmethod
+    def upload_file(self, local_file_path: str, remote_file_path: str) -> None:
+        pass
+
+class S3Provider(StorageProvider):
+    def __init__(self, bucket: str, endpoint_url: str = 'https://s3.cern.ch'):
+        self.bucket = bucket
+        self.s3 = boto3.client('s3', endpoint_url=endpoint_url)
+
+    def list_folders(self, base_path: str) -> list[str]:
+        paginator = self.s3.get_paginator('list_objects_v2')
+        folders = []
+        for page in paginator.paginate(Bucket=self.bucket, Prefix=base_path, Delimiter='/'):
+            for prefix in page.get('CommonPrefixes', []):
+                folders.append(prefix['Prefix'])
+        return folders
+
+    def list_pdfs(self, folder_path: str) -> list[str]:
+        response = self.s3.list_objects_v2(Bucket=self.bucket, Prefix=folder_path)
+        return [
+            obj['Key'] for obj in response.get('Contents', [])
+            if obj['Key'].lower().endswith('.pdf')
+        ]
+
+    def download_to_temp(self, file_path: str, temp_file_path: str) -> None:
+        self.s3.download_file(self.bucket, file_path, temp_file_path)
+
+    def upload_file(self, local_file_path: str, remote_file_path: str) -> None:
+        self.s3.upload_file(local_file_path, self.bucket, remote_file_path)
+
+class CernboxProvider(StorageProvider):
+    def __init__(self, public_link_hash: str, account: str = None, password: str = None):
+        self.public_link_hash = public_link_hash
+        self.account = account
+        self.password = password
+        
+        self.public_base_url = f"https://cernbox.cern.ch/remote.php/dav/public-files/{public_link_hash}"
+
+        if account:
+            self.auth_base_url = f"https://cernbox.cern.ch/remote.php/dav/files/{account}"
+
+    def _propfind(self, path: str, depth: str = "1") -> list[str]:
+        url = f"{self.public_base_url}/{path}".rstrip('/') + '/'
+        headers = {'Depth': depth}
+        
+        response = requests.request('PROPFIND', url, headers=headers)
+        response.raise_for_status()
+
+        root = ET.fromstring(response.content)
+        namespaces = {'d': 'DAV:'}
+        
+        paths = []
+        for response_tag in root.findall('d:response', namespaces)[1:]:
+            href = response_tag.find('d:href', namespaces).text
+            relative_path = href.split(f"/public-files/{self.public_link_hash}/")[-1]
+            paths.append(relative_path)
+        return paths
+
+    def list_folders(self, base_path: str) -> list[str]:
+        all_items = self._propfind(base_path)
+        return [p for p in all_items if p.endswith('/') or "BOITE_" in p]
+
+    def list_pdfs(self, folder_path: str) -> list[str]:
+        all_items = self._propfind(folder_path)
+        return [p for p in all_items if p.lower().endswith('.pdf')]
+
+    def download_to_temp(self, file_path: str, temp_file_path: str) -> None:
+        url = f"{self.public_base_url}/{file_path}"
+        response = requests.get(url, stream=True)
+        response.raise_for_status()
+        with open(temp_file_path, 'wb') as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+
+    def upload_file(self, local_file_path: str, remote_file_path: str) -> None:
+        if not self.account or not self.password:
+            raise ValueError("CERN account and password are required for uploading.")
+            
+        clean_remote_path = remote_file_path.lstrip('/')
+        url = f"{self.auth_base_url}/{clean_remote_path}"
+        
+        with open(local_file_path, 'rb') as f:
+            response = requests.put(url, data=f, auth=(self.account, self.password))
+            
+        response.raise_for_status()
\ No newline at end of file
diff --git a/refactory/test_connections.py b/refactory/test_connections.py
new file mode 100644
index 0000000..56a9de4
--- /dev/null
+++ b/refactory/test_connections.py
@@ -0,0 +1,81 @@
+import tempfile
+import os
+from storage_connection import S3Provider, CernboxProvider
+
+def test_s3():
+    print("--- Testing AWS S3 connection ---")
+    try:
+        s3 = S3Provider(bucket="digitization-dev")
+        base_path = "cern-archives/raw/PDF/"
+        
+        folders = s3.list_folders(base_path)
+        print("✅ Read: Success! Connected to S3.")
+        print(f"Found {len(folders)} folders in '{base_path}'.")
+        
+        print("\n--- Testing S3 Upload ---")
+        remote_test_file = f"{base_path}upload_test_s3.txt"
+        
+        with tempfile.NamedTemporaryFile(delete=False, mode='w', encoding='utf-8') as tmp:
+            tmp.write("Upload test file generated by test_connections.py")
+            tmp_path = tmp.name
+            
+        try:
+            s3.upload_file(tmp_path, remote_test_file)
+            print(f"✅ Write: Success! File sent to: {remote_test_file}")
+        finally:
+            os.remove(tmp_path) 
+            
+    except Exception as e:
+        print(f"❌ Failed to connect/operate on S3.")
+        print(f"Details: {e}")
+
+def test_cernbox():
+    print("\n--- Testing CERNBOX connection (Hybrid Mode) ---")
+    
+    # 1. Read Variables (Public)
+    public_hash = "QslvWRIPsBcDAOK"
+    read_base_path = "" # Relative path inside the public link
+    
+    # 2. Write Variables (Private/Authenticated)
+    cern_user = "" # CERN username
+    cern_password = os.environ.get("CERNBOX_PASSWORD")
+    write_base_path = ""#"eos/user/{u}/{user}/teste/"
+    
+    if public_hash == "PUT_YOUR_PUBLIC_HASH_HERE":
+        print("Warning: Configure the public_hash in the code before testing.")
+        return
+        
+    if not cern_password:
+        print("❌ The CERNBOX_PASSWORD environment variable is not set.")
+        print("Run in terminal: export CERNBOX_PASSWORD='your_password'")
+        return
+
+    try:
+        # Passing all three arguments
+        cernbox = CernboxProvider(public_link_hash=public_hash, account=cern_user, password=cern_password)
+        
+        print("\n[Phase 1: Reading from Public Link]")
+        folders = cernbox.list_folders(read_base_path)
+        print("✅ Read: Success (Anonymous)!")
+        print(f"Found {len(folders)} items at the root of the link.")
+        
+        print("\n[Phase 2: Writing via Authenticated WebDAV]")
+        remote_test_file = f"{write_base_path}hybrid_connection_test.txt"
+        
+        with tempfile.NamedTemporaryFile(delete=False, mode='w', encoding='utf-8') as tmp:
+            tmp.write("Authenticated upload from test_connections.py")
+            tmp_path = tmp.name
+            
+        try:
+            cernbox.upload_file(tmp_path, remote_test_file)
+            print(f"✅ Write: Success (Authenticated)! File sent to: {remote_test_file}")
+        finally:
+            os.remove(tmp_path)
+            
+    except Exception as e:
+        print(f"❌ Failed to connect/operate on CERNBOX.")
+        print(f"Details: {e}")
+
+if __name__ == "__main__":
+    # test_s3()
+    test_cernbox()
\ No newline at end of file
diff --git a/refactory/validate_pdf.py b/refactory/validate_pdf.py
new file mode 100644
index 0000000..0b0ee18
--- /dev/null
+++ b/refactory/validate_pdf.py
@@ -0,0 +1,34 @@
+import os
+from pypdf import PdfReader
+from pypdf.errors import PdfReadError
+
+def is_pdf_valid(file_path: str) -> bool:
+    """Checks if a local PDF is structurally valid and readable."""
+    try:
+        file_size = os.path.getsize(file_path)
+        if file_size < 100:  
+            return False
+
+        with open(file_path, "rb") as f:
+            header = f.read(8)
+            f.seek(-min(1024, file_size), 2)
+            trailer = f.read()
+
+        if not header.startswith(b"%PDF-"):
+            return False
+        if b"%%EOF" not in trailer:
+            return False
+
+        reader = PdfReader(file_path)
+        if len(reader.pages) == 0:
+            return False
+
+        _ = reader.pages[0] 
+
+        return True
+
+    except OSError as e:
+        raise RuntimeError(f"System error when accessing file {file_path}: {e}") from e
+
+    except (PdfReadError, Exception):
+        return False
\ No newline at end of file

From 0637b20f6230a363d90b5e8f02c4c936d5a2dec9 Mon Sep 17 00:00:00 2001
From: Gabriela de Santana Carrara <gabriela.de.santana.carrara@cern.ch>
Date: Tue, 31 Mar 2026 18:25:25 +0200
Subject: [PATCH 2/5] digitization: fix excel files input and other comments

Ref: cern-sis/digitization#22
---
 poetry.lock                     | 229 ++++++++++++++++++++++++++++----
 pyproject.toml                  |   5 +-
 refactory/README.md             |  85 ++++++++++++
 refactory/main.py               | 140 ++++++++++---------
 refactory/storage_connection.py |  29 +++-
 refactory/test_connections.py   |  47 ++++---
 scripts/double_check_pdfs.py    |   2 +-
 7 files changed, 418 insertions(+), 119 deletions(-)
 create mode 100644 refactory/README.md

diff --git a/poetry.lock b/poetry.lock
index d8d0e3b..d22fc24 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -105,6 +105,18 @@ urllib3 = {version = ">=1.25.4,<2.2.0 || >2.2.0,<3", markers = "python_version >
 [package.extras]
 crt = ["awscrt (==0.23.8)"]
 
+[[package]]
+name = "certifi"
+version = "2026.2.25"
+description = "Python package for providing Mozilla's CA Bundle."
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "certifi-2026.2.25-py3-none-any.whl", hash = "sha256:027692e4402ad994f1c42e52a4997a9763c646b73e4096e4d5d6db8af1d6f0fa"},
+    {file = "certifi-2026.2.25.tar.gz", hash = "sha256:e887ab5cee78ea814d3472169153c2d12cd43b14bd03329a39a9c6e2e80bfba7"},
+]
+
 [[package]]
 name = "cffi"
 version = "1.17.1"
@@ -185,6 +197,145 @@ files = [
 [package.dependencies]
 pycparser = "*"
 
+[[package]]
+name = "charset-normalizer"
+version = "3.4.6"
+description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "charset_normalizer-3.4.6-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:2e1d8ca8611099001949d1cdfaefc510cf0f212484fe7c565f735b68c78c3c95"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e25369dc110d58ddf29b949377a93e0716d72a24f62bad72b2b39f155949c1fd"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:259695e2ccc253feb2a016303543d691825e920917e31f894ca1a687982b1de4"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:dda86aba335c902b6149a02a55b38e96287157e609200811837678214ba2b1db"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:51fb3c322c81d20567019778cb5a4a6f2dc1c200b886bc0d636238e364848c89"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-manylinux_2_31_armv7l.whl", hash = "sha256:4482481cb0572180b6fd976a4d5c72a30263e98564da68b86ec91f0fe35e8565"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:39f5068d35621da2881271e5c3205125cc456f54e9030d3f723288c873a71bf9"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:8bea55c4eef25b0b19a0337dc4e3f9a15b00d569c77211fa8cde38684f234fb7"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:f0cdaecd4c953bfae0b6bb64910aaaca5a424ad9c72d85cb88417bb9814f7550"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:150b8ce8e830eb7ccb029ec9ca36022f756986aaaa7956aad6d9ec90089338c0"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:e68c14b04827dd76dcbd1aeea9e604e3e4b78322d8faf2f8132c7138efa340a8"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:3778fd7d7cd04ae8f54651f4a7a0bd6e39a0cf20f801720a4c21d80e9b7ad6b0"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:dad6e0f2e481fffdcf776d10ebee25e0ef89f16d691f1e5dee4b586375fdc64b"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-win32.whl", hash = "sha256:74a2e659c7ecbc73562e2a15e05039f1e22c75b7c7618b4b574a3ea9118d1557"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-win_amd64.whl", hash = "sha256:aa9cccf4a44b9b62d8ba8b4dd06c649ba683e4bf04eea606d2e94cfc2d6ff4d6"},
+    {file = "charset_normalizer-3.4.6-cp310-cp310-win_arm64.whl", hash = "sha256:e985a16ff513596f217cee86c21371b8cd011c0f6f056d0920aa2d926c544058"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:82060f995ab5003a2d6e0f4ad29065b7672b6593c8c63559beefe5b443242c3e"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:60c74963d8350241a79cb8feea80e54d518f72c26db618862a8f53e5023deaf9"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f6e4333fb15c83f7d1482a76d45a0818897b3d33f00efd215528ff7c51b8e35d"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:bc72863f4d9aba2e8fd9085e63548a324ba706d2ea2c83b260da08a59b9482de"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9cc4fc6c196d6a8b76629a70ddfcd4635a6898756e2d9cac5565cf0654605d73"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-manylinux_2_31_armv7l.whl", hash = "sha256:0c173ce3a681f309f31b87125fecec7a5d1347261ea11ebbb856fa6006b23c8c"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c907cdc8109f6c619e6254212e794d6548373cc40e1ec75e6e3823d9135d29cc"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:404a1e552cf5b675a87f0651f8b79f5f1e6fd100ee88dc612f89aa16abd4486f"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:e3c701e954abf6fc03a49f7c579cc80c2c6cc52525340ca3186c41d3f33482ef"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:7a6967aaf043bceabab5412ed6bd6bd26603dae84d5cb75bf8d9a74a4959d398"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:5feb91325bbceade6afab43eb3b508c63ee53579fe896c77137ded51c6b6958e"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:f820f24b09e3e779fe84c3c456cb4108a7aa639b0d1f02c28046e11bfcd088ed"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b35b200d6a71b9839a46b9b7fff66b6638bb52fc9658aa58796b0326595d3021"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-win32.whl", hash = "sha256:9ca4c0b502ab399ef89248a2c84c54954f77a070f28e546a85e91da627d1301e"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-win_amd64.whl", hash = "sha256:a9e68c9d88823b274cf1e72f28cb5dc89c990edf430b0bfd3e2fb0785bfeabf4"},
+    {file = "charset_normalizer-3.4.6-cp311-cp311-win_arm64.whl", hash = "sha256:97d0235baafca5f2b09cf332cc275f021e694e8362c6bb9c96fc9a0eb74fc316"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:2ef7fedc7a6ecbe99969cd09632516738a97eeb8bd7258bf8a0f23114c057dab"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a4ea868bc28109052790eb2b52a9ab33f3aa7adc02f96673526ff47419490e21"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:836ab36280f21fc1a03c99cd05c6b7af70d2697e374c7af0b61ed271401a72a2"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:f1ce721c8a7dfec21fcbdfe04e8f68174183cf4e8188e0645e92aa23985c57ff"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0e28d62a8fc7a1fa411c43bd65e346f3bce9716dc51b897fbe930c5987b402d5"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-manylinux_2_31_armv7l.whl", hash = "sha256:530d548084c4a9f7a16ed4a294d459b4f229db50df689bfe92027452452943a0"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:30f445ae60aad5e1f8bdbb3108e39f6fbc09f4ea16c815c66578878325f8f15a"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:ac2393c73378fea4e52aa56285a3d64be50f1a12395afef9cce47772f60334c2"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:90ca27cd8da8118b18a52d5f547859cc1f8354a00cd1e8e5120df3e30d6279e5"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:8e5a94886bedca0f9b78fecd6afb6629142fd2605aa70a125d49f4edc6037ee6"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:695f5c2823691a25f17bc5d5ffe79fa90972cc34b002ac6c843bb8a1720e950d"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:231d4da14bcd9301310faf492051bee27df11f2bc7549bc0bb41fef11b82daa2"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:a056d1ad2633548ca18ffa2f85c202cfb48b68615129143915b8dc72a806a923"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-win32.whl", hash = "sha256:c2274ca724536f173122f36c98ce188fd24ce3dad886ec2b7af859518ce008a4"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-win_amd64.whl", hash = "sha256:c8ae56368f8cc97c7e40a7ee18e1cedaf8e780cd8bc5ed5ac8b81f238614facb"},
+    {file = "charset_normalizer-3.4.6-cp312-cp312-win_arm64.whl", hash = "sha256:899d28f422116b08be5118ef350c292b36fc15ec2daeb9ea987c89281c7bb5c4"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:11afb56037cbc4b1555a34dd69151e8e069bee82e613a73bef6e714ce733585f"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:423fb7e748a08f854a08a222b983f4df1912b1daedce51a72bd24fe8f26a1843"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:d73beaac5e90173ac3deb9928a74763a6d230f494e4bfb422c217a0ad8e629bf"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d60377dce4511655582e300dc1e5a5f24ba0cb229005a1d5c8d0cb72bb758ab8"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:530e8cebeea0d76bdcf93357aa5e41336f48c3dc709ac52da2bb167c5b8271d9"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-manylinux_2_31_armv7l.whl", hash = "sha256:a26611d9987b230566f24a0a125f17fe0de6a6aff9f25c9f564aaa2721a5fb88"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:34315ff4fc374b285ad7f4a0bf7dcbfe769e1b104230d40f49f700d4ab6bbd84"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:5f8ddd609f9e1af8c7bd6e2aca279c931aefecd148a14402d4e368f3171769fd"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:80d0a5615143c0b3225e5e3ef22c8d5d51f3f72ce0ea6fb84c943546c7b25b6c"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:92734d4d8d187a354a556626c221cd1a892a4e0802ccb2af432a1d85ec012194"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:613f19aa6e082cf96e17e3ffd89383343d0d589abda756b7764cf78361fd41dc"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:2b1a63e8224e401cafe7739f77efd3f9e7f5f2026bda4aead8e59afab537784f"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6cceb5473417d28edd20c6c984ab6fee6c6267d38d906823ebfe20b03d607dc2"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-win32.whl", hash = "sha256:d7de2637729c67d67cf87614b566626057e95c303bc0a55ffe391f5205e7003d"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-win_amd64.whl", hash = "sha256:572d7c822caf521f0525ba1bce1a622a0b85cf47ffbdae6c9c19e3b5ac3c4389"},
+    {file = "charset_normalizer-3.4.6-cp313-cp313-win_arm64.whl", hash = "sha256:a4474d924a47185a06411e0064b803c68be044be2d60e50e8bddcc2649957c1f"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:9cc6e6d9e571d2f863fa77700701dae73ed5f78881efc8b3f9a4398772ff53e8"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ef5960d965e67165d75b7c7ffc60a83ec5abfc5c11b764ec13ea54fbef8b4421"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:b3694e3f87f8ac7ce279d4355645b3c878d24d1424581b46282f24b92f5a4ae2"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:5d11595abf8dd942a77883a39d81433739b287b6aa71620f15164f8096221b30"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7bda6eebafd42133efdca535b04ccb338ab29467b3f7bf79569883676fc628db"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-manylinux_2_31_armv7l.whl", hash = "sha256:bbc8c8650c6e51041ad1be191742b8b421d05bbd3410f43fa2a00c8db87678e8"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:22c6f0c2fbc31e76c3b8a86fba1a56eda6166e238c29cdd3d14befdb4a4e4815"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:7edbed096e4a4798710ed6bc75dcaa2a21b68b6c356553ac4823c3658d53743a"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:7f9019c9cb613f084481bd6a100b12e1547cf2efe362d873c2e31e4035a6fa43"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:58c948d0d086229efc484fe2f30c2d382c86720f55cd9bc33591774348ad44e0"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:419a9d91bd238052642a51938af8ac05da5b3343becde08d5cdeab9046df9ee1"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:5273b9f0b5835ff0350c0828faea623c68bfa65b792720c453e22b25cc72930f"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:0e901eb1049fdb80f5bd11ed5ea1e498ec423102f7a9b9e4645d5b8204ff2815"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-win32.whl", hash = "sha256:b4ff1d35e8c5bd078be89349b6f3a845128e685e751b6ea1169cf2160b344c4d"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-win_amd64.whl", hash = "sha256:74119174722c4349af9708993118581686f343adc1c8c9c007d59be90d077f3f"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314-win_arm64.whl", hash = "sha256:e5bcc1a1ae744e0bb59641171ae53743760130600da8db48cbb6e4918e186e4e"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:ad8faf8df23f0378c6d527d8b0b15ea4a2e23c89376877c598c4870d1b2c7866"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f5ea69428fa1b49573eef0cc44a1d43bebd45ad0c611eb7d7eac760c7ae771bc"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:06a7e86163334edfc5d20fe104db92fcd666e5a5df0977cb5680a506fe26cc8e"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:e1f6e2f00a6b8edb562826e4632e26d063ac10307e80f7461f7de3ad8ef3f077"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:95b52c68d64c1878818687a473a10547b3292e82b6f6fe483808fb1468e2f52f"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:7504e9b7dc05f99a9bbb4525c67a2c155073b44d720470a148b34166a69c054e"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:172985e4ff804a7ad08eebec0a1640ece87ba5041d565fff23c8f99c1f389484"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:4be9f4830ba8741527693848403e2c457c16e499100963ec711b1c6f2049b7c7"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:79090741d842f564b1b2827c0b82d846405b744d31e84f18d7a7b41c20e473ff"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:87725cfb1a4f1f8c2fc9890ae2f42094120f4b44db9360be5d99a4c6b0e03a9e"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:fcce033e4021347d80ed9c66dcf1e7b1546319834b74445f561d2e2221de5659"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:ca0276464d148c72defa8bb4390cce01b4a0e425f3b50d1435aa6d7a18107602"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:197c1a244a274bb016dd8b79204850144ef77fe81c5b797dc389327adb552407"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-win32.whl", hash = "sha256:2a24157fa36980478dd1770b585c0f30d19e18f4fb0c47c13aa568f871718579"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-win_amd64.whl", hash = "sha256:cd5e2801c89992ed8c0a3f0293ae83c159a60d9a5d685005383ef4caca77f2c4"},
+    {file = "charset_normalizer-3.4.6-cp314-cp314t-win_arm64.whl", hash = "sha256:47955475ac79cc504ef2704b192364e51d0d473ad452caedd0002605f780101c"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:659a1e1b500fac8f2779dd9e1570464e012f43e580371470b45277a27baa7532"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f61aa92e4aad0be58eb6eb4e0c21acf32cf8065f4b2cae5665da756c4ceef982"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f50498891691e0864dc3da965f340fada0771f6142a378083dc4608f4ea513e2"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:bf625105bb9eef28a56a943fec8c8a98aeb80e7d7db99bd3c388137e6eb2d237"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2bd9d128ef93637a5d7a6af25363cf5dec3fa21cf80e68055aad627f280e8afa"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-manylinux_2_31_armv7l.whl", hash = "sha256:d08ec48f0a1c48d75d0356cea971921848fb620fdeba805b28f937e90691209f"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:1ed80ff870ca6de33f4d953fda4d55654b9a2b340ff39ab32fa3adbcd718f264"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:f98059e4fcd3e3e4e2d632b7cf81c2faae96c43c60b569e9c621468082f1d104"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-musllinux_1_2_armv7l.whl", hash = "sha256:ab30e5e3e706e3063bc6de96b118688cb10396b70bb9864a430f67df98c61ecc"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:d5f5d1e9def3405f60e3ca8232d56f35c98fb7bf581efcc60051ebf53cb8b611"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-musllinux_1_2_riscv64.whl", hash = "sha256:461598cd852bfa5a61b09cae2b1c02e2efcd166ee5516e243d540ac24bfa68a7"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-musllinux_1_2_s390x.whl", hash = "sha256:71be7e0e01753a89cf024abf7ecb6bca2c81738ead80d43004d9b5e3f1244e64"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:df01808ee470038c3f8dc4f48620df7225c49c2d6639e38f96e6d6ac6e6f7b0e"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-win32.whl", hash = "sha256:69dd852c2f0ad631b8b60cfbe25a28c0058a894de5abb566619c205ce0550eae"},
+    {file = "charset_normalizer-3.4.6-cp38-cp38-win_amd64.whl", hash = "sha256:517ad0e93394ac532745129ceabdf2696b609ec9f87863d337140317ebce1c14"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:31215157227939b4fb3d740cd23fe27be0439afef67b785a1eb78a3ae69cba9e"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ecbbd45615a6885fe3240eb9db73b9e62518b611850fdf8ab08bd56de7ad2b17"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c45a03a4c69820a399f1dda9e1d8fbf3562eda46e7720458180302021b08f778"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:e8aeb10fcbe92767f0fa69ad5a72deca50d0dca07fbde97848997d778a50c9fe"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:54fae94be3d75f3e573c9a1b5402dc593de19377013c9a0e4285e3d402dd3a2a"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-manylinux_2_31_armv7l.whl", hash = "sha256:2f7fdd9b6e6c529d6a2501a2d36b240109e78a8ceaef5687cfcfa2bbe671d297"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:4d1d02209e06550bdaef34af58e041ad71b88e624f5d825519da3a3308e22687"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:8bc5f0687d796c05b1e28ab0d38a50e6309906ee09375dd3aff6a9c09dd6e8f4"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-musllinux_1_2_armv7l.whl", hash = "sha256:ee4ec14bc1680d6b0afab9aea2ef27e26d2024f18b24a2d7155a52b60da7e833"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:d1a2ee9c1499fc8f86f4521f27a973c914b211ffa87322f4ee33bb35392da2c5"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-musllinux_1_2_riscv64.whl", hash = "sha256:48696db7f18afb80a068821504296eb0787d9ce239b91ca15059d1d3eaacf13b"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:4f41da960b196ea355357285ad1316a00099f22d0929fe168343b99b254729c9"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:802168e03fba8bbc5ce0d866d589e4b1ca751d06edee69f7f3a19c5a9fe6b597"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-win32.whl", hash = "sha256:8761ac29b6c81574724322a554605608a9960769ea83d2c73e396f3df896ad54"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-win_amd64.whl", hash = "sha256:1cf0a70018692f85172348fe06d3a4b63f94ecb055e13a00c644d368eb82e5b8"},
+    {file = "charset_normalizer-3.4.6-cp39-cp39-win_arm64.whl", hash = "sha256:3516bbb8d42169de9e61b8520cbeeeb716f12f4ecfe3fd30a9919aa16c806ca8"},
+    {file = "charset_normalizer-3.4.6-py3-none-any.whl", hash = "sha256:947cf925bc916d90adba35a64c82aace04fa39b46b52d4630ece166655905a69"},
+    {file = "charset_normalizer-3.4.6.tar.gz", hash = "sha256:1ae6b62897110aa7c79ea2f5dd38d1abca6db663687c0b1ad9aed6f6bae3d9d6"},
+]
+
 [[package]]
 name = "click"
 version = "8.1.8"
@@ -264,31 +415,32 @@ test = ["certifi", "cryptography-vectors (==43.0.3)", "pretend", "pytest (>=6.2.
 test-randomorder = ["pytest-randomly"]
 
 [[package]]
-name = "dotenv"
-version = "0.9.9"
-description = "Deprecated package"
+name = "et-xmlfile"
+version = "2.0.0"
+description = "An implementation of lxml.xmlfile for the standard library"
 optional = false
-python-versions = "*"
+python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "dotenv-0.9.9-py2.py3-none-any.whl", hash = "sha256:29cf74a087b31dafdb5a446b6d7e11cbce8ed2741540e2339c69fbef92c94ce9"},
+    {file = "et_xmlfile-2.0.0-py3-none-any.whl", hash = "sha256:7a91720bc756843502c3b7504c77b8fe44217c85c537d85037f0f536151b2caa"},
+    {file = "et_xmlfile-2.0.0.tar.gz", hash = "sha256:dab3f4764309081ce75662649be815c4c9081e88f0837825f90fd28317d4da54"},
 ]
 
-[package.dependencies]
-python-dotenv = "*"
-
 [[package]]
-name = "et-xmlfile"
-version = "2.0.0"
-description = "An implementation of lxml.xmlfile for the standard library"
+name = "idna"
+version = "3.11"
+description = "Internationalized Domain Names in Applications (IDNA)"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "et_xmlfile-2.0.0-py3-none-any.whl", hash = "sha256:7a91720bc756843502c3b7504c77b8fe44217c85c537d85037f0f536151b2caa"},
-    {file = "et_xmlfile-2.0.0.tar.gz", hash = "sha256:dab3f4764309081ce75662649be815c4c9081e88f0837825f90fd28317d4da54"},
+    {file = "idna-3.11-py3-none-any.whl", hash = "sha256:771a87f49d9defaf64091e6e6fe9c18d4833f140bd19464795bc32d966ca37ea"},
+    {file = "idna-3.11.tar.gz", hash = "sha256:795dafcc9c04ed0c1fb032c2aa73654d8e8c5023a7df64a53f39190ada629902"},
 ]
 
+[package.extras]
+all = ["flake8 (>=7.1.1)", "mypy (>=1.11.2)", "pytest (>=8.3.2)", "ruff (>=0.6.2)"]
+
 [[package]]
 name = "jmespath"
 version = "1.0.1"
@@ -526,23 +678,24 @@ docs = ["sphinx (>=1.6.5)", "sphinx-rtd-theme"]
 tests = ["hypothesis (>=3.27.0)", "pytest (>=3.2.1,!=3.3.0)"]
 
 [[package]]
-name = "pypdf2"
-version = "3.0.1"
+name = "pypdf"
+version = "6.9.2"
 description = "A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files"
 optional = false
-python-versions = ">=3.6"
+python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "PyPDF2-3.0.1.tar.gz", hash = "sha256:a74408f69ba6271f71b9352ef4ed03dc53a31aa404d29b5d31f53bfecfee1440"},
-    {file = "pypdf2-3.0.1-py3-none-any.whl", hash = "sha256:d16e4205cfee272fbdc0568b68d82be796540b1537508cef59388f839c191928"},
+    {file = "pypdf-6.9.2-py3-none-any.whl", hash = "sha256:662cf29bcb419a36a1365232449624ab40b7c2d0cfc28e54f42eeecd1fd7e844"},
+    {file = "pypdf-6.9.2.tar.gz", hash = "sha256:7f850faf2b0d4ab936582c05da32c52214c2b089d61a316627b5bfb5b0dab46c"},
 ]
 
 [package.extras]
-crypto = ["PyCryptodome"]
-dev = ["black", "flit", "pip-tools", "pre-commit (<2.18.0)", "pytest-cov", "wheel"]
+crypto = ["cryptography"]
+cryptodome = ["PyCryptodome"]
+dev = ["flit", "pip-tools", "pre-commit", "pytest-cov", "pytest-socket", "pytest-timeout", "pytest-xdist", "wheel"]
 docs = ["myst_parser", "sphinx", "sphinx_rtd_theme"]
-full = ["Pillow", "PyCryptodome"]
-image = ["Pillow"]
+full = ["Pillow (>=8.0.0)", "cryptography"]
+image = ["Pillow (>=8.0.0)"]
 
 [[package]]
 name = "pysftp"
@@ -575,14 +728,14 @@ six = ">=1.5"
 
 [[package]]
 name = "python-dotenv"
-version = "1.1.1"
+version = "1.2.2"
 description = "Read key-value pairs from a .env file and set them as environment variables"
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.10"
 groups = ["main"]
 files = [
-    {file = "python_dotenv-1.1.1-py3-none-any.whl", hash = "sha256:31f23644fe2602f88ff55e1f5c79ba497e01224ee7737937930c448e4d0e24dc"},
-    {file = "python_dotenv-1.1.1.tar.gz", hash = "sha256:a8a6399716257f45be6a007360200409fce5cda2661e3dec71d23dc15f6189ab"},
+    {file = "python_dotenv-1.2.2-py3-none-any.whl", hash = "sha256:1d8214789a24de455a8b8bd8ae6fe3c6b69a5e3d64aa8a8e5d68e694bbcb285a"},
+    {file = "python_dotenv-1.2.2.tar.gz", hash = "sha256:2c371a91fbd7ba082c2c1dc1f8bf89ca22564a087c2c287cd9b662adde799cf3"},
 ]
 
 [package.extras]
@@ -600,6 +753,28 @@ files = [
     {file = "pytz-2025.2.tar.gz", hash = "sha256:360b9e3dbb49a209c21ad61809c7fb453643e048b38924c765813546746e81c3"},
 ]
 
+[[package]]
+name = "requests"
+version = "2.33.1"
+description = "Python HTTP for Humans."
+optional = false
+python-versions = ">=3.10"
+groups = ["main"]
+files = [
+    {file = "requests-2.33.1-py3-none-any.whl", hash = "sha256:4e6d1ef462f3626a1f0a0a9c42dd93c63bad33f9f1c1937509b8c5c8718ab56a"},
+    {file = "requests-2.33.1.tar.gz", hash = "sha256:18817f8c57c6263968bc123d237e3b8b08ac046f5456bd1e307ee8f4250d3517"},
+]
+
+[package.dependencies]
+certifi = ">=2023.5.7"
+charset_normalizer = ">=2,<4"
+idna = ">=2.5,<4"
+urllib3 = ">=1.26,<3"
+
+[package.extras]
+socks = ["PySocks (>=1.5.6,!=1.5.7)"]
+use-chardet-on-py3 = ["chardet (>=3.0.2,<8)"]
+
 [[package]]
 name = "s3transfer"
 version = "0.12.0"
@@ -685,4 +860,4 @@ zstd = ["zstandard (>=0.18.0)"]
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.12"
-content-hash = "afbee7892d433bfd5919d3f2c96e6dd1d7d0e9d127008ab1f6af8f80e4279812"
+content-hash = "28dcb5ac54f21265b9c426938c63001062f89b60720411dd9bcde02ceef93714"
diff --git a/pyproject.toml b/pyproject.toml
index e05c8a3..d990287 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -9,11 +9,12 @@ python = "^3.12"
 pysftp = "^0.2.9"
 click = "^8.0.3"
 boto3 = "^1.38.9"
+requests = "^2.31.0"
+python-dotenv = "^1.0.0"
 pandas = "^2.2.3"
 openpyxl = "^3.1.5"
 tqdm = "^4.67.1"
-pypdf2 = "^3.0.1"
-dotenv = "^0.9.9"
+pypdf = "^6.9.2"
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]
diff --git a/refactory/README.md b/refactory/README.md
new file mode 100644
index 0000000..f5f3121
--- /dev/null
+++ b/refactory/README.md
@@ -0,0 +1,85 @@
+# refactory
+
+This directory contains scripts and helpers for validating PDF files in an S3 bucket using an inventory of Excel files hosted on CERNBox.
+
+## Structure
+
+- `main.py` - main script that validates PDFs using the CERNBox inventory.
+- `storage_connection.py` - storage provider abstraction:
+  - `S3Provider` for S3.
+  - `CernboxProvider` for public CERNBox access.
+- `validate_pdf.py` - validates PDFs locally with `is_pdf_valid(file_path)`.
+- `test_connections.py` - testing/connection experiment script.
+
+## Dependencies
+
+This project uses Poetry to manage dependencies. The required libraries are listed in `pyproject.toml`.
+
+### Install dependencies with Poetry
+
+```bash
+poetry install
+```
+
+### Main dependencies
+
+- `boto3`
+- `requests`
+- `pypdf`
+
+> If the project is managed with Poetry, `requirements.txt` is not required.
+
+## AWS Authentication
+
+`S3Provider` uses `boto3`. Configure credentials using environment variables or the default AWS config files:
+
+- `AWS_ACCESS_KEY_ID`
+- `AWS_SECRET_ACCESS_KEY`
+
+### Example environment variables
+
+```bash
+export ACCESS_KEY="YOUR_ACCESS_KEY"
+export SECRET_KEY="YOUR_SECRET_KEY"
+```
+
+### Supported alternatives
+
+- `~/.aws/credentials`
+- `~/.aws/config`
+- IAM role attached to an instance/container
+
+> `S3Provider` also supports the default endpoint `https://s3.cern.ch`, configured in `storage_connection.py`.
+
+## Usage with Poetry
+
+Run the main script via Poetry:
+
+```bash
+poetry run python refactory/main.py <target_excel_hash> <upload_reports>
+```
+
+Parameters:
+
+- `target_excel_hash`: public CERNBox hash containing the inventory Excel files.
+- `upload_reports`: `0` to skip report upload, `1` to upload generated reports back to the S3 bucket. 
+
+### Example
+
+```bash
+poetry run python refactory/main.py QslvWRIPsBcDAOK 0
+```
+
+## Expected output
+
+The script generates:
+
+- `s3_pdf_issues.log` - text log with valid and corrupted files.
+- `s3_pdf_issues.json` - structured report with metadata, statistics, and file lists.
+
+If `upload_reports=1`, the reports are also uploaded back to the S3 bucket.
+
+## Additional notes
+
+- If CERNBox upload requires authentication, provide `account` and `password` to `CernboxProvider`.
+- Use `test_connections.py` to verify connections before running the main pipeline.
diff --git a/refactory/main.py b/refactory/main.py
index 5594b77..d61f1ba 100644
--- a/refactory/main.py
+++ b/refactory/main.py
@@ -6,86 +6,100 @@
 from storage_connection import StorageProvider, S3Provider, CernboxProvider
 from validate_pdf import is_pdf_valid
 
-def run_validation_pipeline(provider: StorageProvider, base_path: str, log_file: str, start: int = None, end: int = None, upload_reports: bool = False):
-    """Navigates directories, validates files, and logs corrupted files."""
-    print(f"Discovering folders in: {base_path}")
-    
+
+def run_validation_pipeline(
+    provider: StorageProvider,
+    base_path: str,
+    log_file: str,
+    target_excel_hash: str,
+    upload_reports: bool = False,
+):
+    print(type(upload_reports),bool(upload_reports))
+    """Navigates directories, validates files, and logs files status."""
+    inventory_provider = CernboxProvider(target_excel_hash)
+    excel_files = inventory_provider.list_excel("")
+
+    target_box_numbers = set()
+    for file_path in excel_files:
+        filename = file_path.split(".")[0]
+
+        match = re.search(r"(?i:BOITE)[\-_]O0(\d+)(-\w+)?", filename)
+
+        if match:
+            target_box_numbers.add(int(match.group(1)))
+    print(f"Excel files: {len(target_box_numbers)} boxes to check.")
+
+    print(f"Folders in: {base_path}")
     folders = provider.list_folders(base_path)
-    
+
     if not folders:
         print("No folders found in this path.")
         return
 
-    found_box_numbers = set()
-    empty_folders = []
+    found_and_valid_boxes = set()
     corrupted_files = []
-    valid_files_count = 0
+    valid_files = []
 
     print("Starting validation...")
 
     for folder in folders:
-        if "BOITE_" not in folder:
+        match = re.search(r"(?i:BOITE)[\-_]O0(\d+)(-\w+)?", folder)
+        if not match:
             continue
 
-        match = re.search(r"BOITE_O0(\d+)", folder)
-        if match:
-            box_num = int(match.group(1))
-            if start is not None and box_num < start:
-                continue
-            if end is not None and box_num > end:
-                continue
-            
-            found_box_numbers.add(box_num)
-        else:
+        box_num = int(match.group(1))
+        if box_num not in target_box_numbers:
             continue
-            
-        print(f"\nChecking folder: {folder}")
+        print(f"Processing target Box: {match.group(1) + (match.group(2) or '')}")
+
         pdf_files = provider.list_pdfs(folder)
 
         if not pdf_files:
-            print("   Empty folder or no PDFs.")
-            empty_folders.append(folder)
+            print(f"⚠️ EMPTY FOLDER: {folder}")
             continue
 
-        for file_path in pdf_files:
-            print(f"   {file_path.split('/')[-1]} ... ", end="")
-            
+        found_and_valid_boxes.add(box_num)
+
+        for pdf_path in pdf_files:
             with tempfile.NamedTemporaryFile(delete=True) as tmp:
-                provider.download_to_temp(file_path, tmp.name)
-                valid = is_pdf_valid(tmp.name)
-            
-            if valid:
-                print("✅ Valid")
-                valid_files_count += 1
-            else:
-                print("❌ Corrupted")
-                corrupted_files.append(file_path)
+                provider.download_to_temp(pdf_path, tmp.name)
+
+                if is_pdf_valid(tmp.name):
+                    valid_files.append(pdf_path)
+                    print(f"  ✅ {pdf_path}")
+                else:
+                    print(f"  ❌ CORRUPTED: {pdf_path}")
+                    corrupted_files.append(pdf_path)
+    missing_boxes = target_box_numbers - found_and_valid_boxes
+
+    if missing_boxes:
+        print("\n🚨 Empty target boxes:")
+        for box in sorted(missing_boxes):
+            print(
+                f"  -> BOITE_O0{box}"
+            )
 
     with open(log_file, "w", encoding="utf-8") as log:
+        log.write(
+            f"Validation report for the following boxes {target_box_numbers}\n ✅ Valid Files: {len(valid_files)}\n ❌ Corrupted Files: {len(corrupted_files)}\n"
+        )
+        for vf in valid_files:
+            log.write(f"✅ Valid PDF: {vf}\n")
         for cf in corrupted_files:
-            log.write(f"Corrupted PDF: {cf}\n")
-
-    missing_boxes = []
-    if start is not None and end is not None:
-        expected_boxes = set(range(start, end + 1))
-        missing_boxes = sorted(list(expected_boxes - found_box_numbers))
+            log.write(f"❌ Corrupted PDF: {cf}\n")
 
     json_report = {
-        "metadata": {
-            "base_path": base_path,
-            "range_analyzed": {"start": start, "end": end}
-        },
+        "metadata": {"base_path": base_path, "target_boxes": list(target_box_numbers)},
         "statistics": {
-            "valid_files": valid_files_count,
+            "valid_files_count": len(valid_files),
             "corrupted_files_count": len(corrupted_files),
-            "empty_folders_count": len(empty_folders),
-            "missing_boxes_count": len(missing_boxes) if missing_boxes else 0
+            "missing_boxes_count": len(missing_boxes) if missing_boxes else 0,
+        },
+        "output": {
+            "valid_files": valid_files,
+            "missing_boxes": list(missing_boxes) if missing_boxes else [],
+            "corrupted_files": corrupted_files,
         },
-        "issues": {
-            "missing_boxes": missing_boxes if missing_boxes else [],
-            "empty_folders": empty_folders,
-            "corrupted_files": corrupted_files
-        }
     }
 
     json_file_path = log_file.replace(".log", ".json")
@@ -98,24 +112,26 @@ def run_validation_pipeline(provider: StorageProvider, base_path: str, log_file:
     if upload_reports:
         remote_log_path = f"{base_path.rstrip('/')}/{os.path.basename(log_file)}"
         remote_json_path = f"{base_path.rstrip('/')}/{os.path.basename(json_file_path)}"
-        
+
         print(f"Uploading reports back to the cloud ({base_path})...")
         try:
             provider.upload_file(log_file, remote_log_path)
             provider.upload_file(json_file_path, remote_json_path)
-            print(f"✅ Upload successful! Files available at: {remote_log_path} and {remote_json_path}")
+            print(
+                f"✅ Upload successful! Files available at: {remote_log_path} and {remote_json_path}"
+            )
         except Exception as e:
             print(f"❌ Failed to upload reports: {e}")
 
+
 if __name__ == "__main__":
     s3_provider = S3Provider(bucket="digitization-dev")
     # cernbox_provider = CernboxProvider(public_link_hash="XjjFxUWUMpuTYCz")
-    
+
     run_validation_pipeline(
-        provider=s3_provider, #cernbox_provider
-        base_path="cern-archives/raw/PDF/", #"teste/", 
+        provider=s3_provider,  # cernbox_provider
+        base_path="cern-archives/raw/PDF/",  # "teste/",
         log_file="s3_pdf_issues.log",
-        start=int(sys.argv[1]), #123
-        end=int(sys.argv[2]), #126
-        upload_reports=sys.argv[3] # 0 | 1 
-    )
\ No newline at end of file
+        target_excel_hash=sys.argv[1],  # public_link_hash
+        upload_reports=int(sys.argv[2]),  # 0 | 1
+    )
diff --git a/refactory/storage_connection.py b/refactory/storage_connection.py
index 7f0bc94..6b48743 100644
--- a/refactory/storage_connection.py
+++ b/refactory/storage_connection.py
@@ -22,10 +22,19 @@ def download_to_temp(self, file_path: str, temp_file_path: str) -> None:
     def upload_file(self, local_file_path: str, remote_file_path: str) -> None:
         pass
 
+    @abstractmethod
+    def list_excel(self, folder_path: str) -> list[str]:
+        pass
+
 class S3Provider(StorageProvider):
     def __init__(self, bucket: str, endpoint_url: str = 'https://s3.cern.ch'):
         self.bucket = bucket
-        self.s3 = boto3.client('s3', endpoint_url=endpoint_url)
+        self.s3 = boto3.client(
+            "s3",
+            aws_access_key_id=os.environ["ACCESS_KEY"],
+            aws_secret_access_key=os.environ["SECRET_KEY"],
+            endpoint_url=endpoint_url,
+        )
 
     def list_folders(self, base_path: str) -> list[str]:
         paginator = self.s3.get_paginator('list_objects_v2')
@@ -47,7 +56,13 @@ def download_to_temp(self, file_path: str, temp_file_path: str) -> None:
 
     def upload_file(self, local_file_path: str, remote_file_path: str) -> None:
         self.s3.upload_file(local_file_path, self.bucket, remote_file_path)
-
+    
+    def list_excel(self, folder_path: str) -> list[str]:
+            response = self.s3.list_objects_v2(Bucket=self.bucket, Prefix=folder_path)
+            return [
+                obj['Key'] for obj in response.get('Contents', [])
+                if obj['Key'].lower().endswith('.xlsx')
+            ]   
 class CernboxProvider(StorageProvider):
     def __init__(self, public_link_hash: str, account: str = None, password: str = None):
         self.public_link_hash = public_link_hash
@@ -55,9 +70,9 @@ def __init__(self, public_link_hash: str, account: str = None, password: str = N
         self.password = password
         
         self.public_base_url = f"https://cernbox.cern.ch/remote.php/dav/public-files/{public_link_hash}"
-
+        
         if account:
-            self.auth_base_url = f"https://cernbox.cern.ch/remote.php/dav/files/{account}"
+            self.auth_base_url = f"https://api.cernbox.cern.ch/remote.php/dav/files/{account}"
 
     def _propfind(self, path: str, depth: str = "1") -> list[str]:
         url = f"{self.public_base_url}/{path}".rstrip('/') + '/'
@@ -92,6 +107,10 @@ def download_to_temp(self, file_path: str, temp_file_path: str) -> None:
             for chunk in response.iter_content(chunk_size=8192):
                 f.write(chunk)
 
+    def list_excel(self, folder_path: str)-> list[str]:
+        all_items = self._propfind(folder_path)
+        return [p for p in all_items if p.lower().endswith('.xlsx')]
+
     def upload_file(self, local_file_path: str, remote_file_path: str) -> None:
         if not self.account or not self.password:
             raise ValueError("CERN account and password are required for uploading.")
@@ -102,4 +121,4 @@ def upload_file(self, local_file_path: str, remote_file_path: str) -> None:
         with open(local_file_path, 'rb') as f:
             response = requests.put(url, data=f, auth=(self.account, self.password))
             
-        response.raise_for_status()
\ No newline at end of file
+        response.raise_for_status()
diff --git a/refactory/test_connections.py b/refactory/test_connections.py
index 56a9de4..ad34e99 100644
--- a/refactory/test_connections.py
+++ b/refactory/test_connections.py
@@ -11,22 +11,24 @@ def test_s3():
         folders = s3.list_folders(base_path)
         print("✅ Read: Success! Connected to S3.")
         print(f"Found {len(folders)} folders in '{base_path}'.")
+
+        ### Test Upload
         
-        print("\n--- Testing S3 Upload ---")
-        remote_test_file = f"{base_path}upload_test_s3.txt"
+        # print("\n--- Testing S3 Upload ---")
+        # remote_test_file = f"{base_path}upload_test_s3.txt"
         
-        with tempfile.NamedTemporaryFile(delete=False, mode='w', encoding='utf-8') as tmp:
-            tmp.write("Upload test file generated by test_connections.py")
-            tmp_path = tmp.name
+        # with tempfile.NamedTemporaryFile(delete=False, mode='w', encoding='utf-8') as tmp:
+        #     tmp.write("Upload test file generated by test_connections.py")
+        #     tmp_path = tmp.name
             
-        try:
-            s3.upload_file(tmp_path, remote_test_file)
-            print(f"✅ Write: Success! File sent to: {remote_test_file}")
-        finally:
-            os.remove(tmp_path) 
+        # try:
+        #     s3.upload_file(tmp_path, remote_test_file)
+        #     print(f"✅ Write: Success! File sent to: {remote_test_file}")
+        # finally:
+        #     os.remove(tmp_path) 
             
     except Exception as e:
-        print(f"❌ Failed to connect/operate on S3.")
+        print("❌ Failed to connect/operate on S3.")
         print(f"Details: {e}")
 
 def test_cernbox():
@@ -37,9 +39,9 @@ def test_cernbox():
     read_base_path = "" # Relative path inside the public link
     
     # 2. Write Variables (Private/Authenticated)
-    cern_user = "" # CERN username
+    cern_user = "gadesant" # CERN username
     cern_password = os.environ.get("CERNBOX_PASSWORD")
-    write_base_path = ""#"eos/user/{u}/{user}/teste/"
+    write_base_path = "eos/user/g/gadesant/teste/"#"eos/user/{u}/{user}/teste/"
     
     if public_hash == "PUT_YOUR_PUBLIC_HASH_HERE":
         print("Warning: Configure the public_hash in the code before testing.")
@@ -65,17 +67,18 @@ def test_cernbox():
         with tempfile.NamedTemporaryFile(delete=False, mode='w', encoding='utf-8') as tmp:
             tmp.write("Authenticated upload from test_connections.py")
             tmp_path = tmp.name
-            
-        try:
-            cernbox.upload_file(tmp_path, remote_test_file)
-            print(f"✅ Write: Success (Authenticated)! File sent to: {remote_test_file}")
-        finally:
-            os.remove(tmp_path)
+
+        ### Test Upload
+        # try:
+        #     cernbox.upload_file(tmp_path, remote_test_file)
+        #     print(f"✅ Write: Success (Authenticated)! File sent to: {remote_test_file}")
+        # finally:
+        #     os.remove(tmp_path)
             
     except Exception as e:
-        print(f"❌ Failed to connect/operate on CERNBOX.")
+        print("❌ Failed to connect/operate on CERNBOX.")
         print(f"Details: {e}")
 
 if __name__ == "__main__":
-    # test_s3()
-    test_cernbox()
\ No newline at end of file
+    test_s3()
+    # test_cernbox()
diff --git a/scripts/double_check_pdfs.py b/scripts/double_check_pdfs.py
index f4e2625..8780bb5 100644
--- a/scripts/double_check_pdfs.py
+++ b/scripts/double_check_pdfs.py
@@ -1,6 +1,6 @@
 import boto3
 import tempfile
-from PyPDF2 import PdfReader
+from pypdf import PdfReader
 import os
 
 def get_s3_client():

From 80d7da27b3b69e0a4349f4f4d9992e01ed8251ec Mon Sep 17 00:00:00 2001
From: Gabriela de Santana Carrara <gabriela.de.santana.carrara@cern.ch>
Date: Tue, 31 Mar 2026 18:34:34 +0200
Subject: [PATCH 3/5] remove requirements from gitignore

---
 .gitignore       | 4 +---
 requirements.txt | 3 +++
 2 files changed, 4 insertions(+), 3 deletions(-)
 create mode 100644 requirements.txt

diff --git a/.gitignore b/.gitignore
index 8d48b18..b5aa617 100644
--- a/.gitignore
+++ b/.gitignore
@@ -17,6 +17,4 @@ import_xml_files/
 # Virtual environments
 .venv
 
-
-requirements.txt
-s3_pdf_issues.json
\ No newline at end of file
+s3_pdf_issues.json
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..d9af537
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,3 @@
+boto3
+requests
+pypdf
\ No newline at end of file

From d92b7a062a309daa5b3241ad32b906499fc83c7f Mon Sep 17 00:00:00 2001
From: Gabriela de Santana Carrara <gabriela.de.santana.carrara@cern.ch>
Date: Wed, 1 Apr 2026 13:47:40 +0200
Subject: [PATCH 4/5] remove debug print

---
 refactory/main.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/refactory/main.py b/refactory/main.py
index d61f1ba..9876cb3 100644
--- a/refactory/main.py
+++ b/refactory/main.py
@@ -14,7 +14,6 @@ def run_validation_pipeline(
     target_excel_hash: str,
     upload_reports: bool = False,
 ):
-    print(type(upload_reports),bool(upload_reports))
     """Navigates directories, validates files, and logs files status."""
     inventory_provider = CernboxProvider(target_excel_hash)
     excel_files = inventory_provider.list_excel("")

From 95ecdd32b0415ec9a0bad82f1898f6eba5e24a48 Mon Sep 17 00:00:00 2001
From: Gabriela de Santana Carrara <gabriela.de.santana.carrara@cern.ch>
Date: Wed, 8 Apr 2026 17:11:21 +0200
Subject: [PATCH 5/5] add cli and array and range as valid inputs

---
 pyproject.toml                  |  1 +
 refactory/README.md             | 42 +++++++++++++-----
 refactory/cli.py                | 76 +++++++++++++++++++++++++++++++++
 refactory/main.py               | 31 ++++++++------
 refactory/storage_connection.py | 32 +++++++-------
 refactory/test_connections.py   | 40 ++++-------------
 requirements.txt                |  6 +--
 7 files changed, 154 insertions(+), 74 deletions(-)
 create mode 100644 refactory/cli.py

diff --git a/pyproject.toml b/pyproject.toml
index d990287..f1ab434 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -22,3 +22,4 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry.scripts]
 digitization = "digitization.cli:digitization"
+digitization_v2 = "refactory.cli:digitization_v2"
diff --git a/refactory/README.md b/refactory/README.md
index f5f3121..43aae66 100644
--- a/refactory/README.md
+++ b/refactory/README.md
@@ -53,33 +53,53 @@ export SECRET_KEY="YOUR_SECRET_KEY"
 
 ## Usage with Poetry
 
-Run the main script via Poetry:
+Run the refactored CLI via Poetry:
 
 ```bash
-poetry run python refactory/main.py <target_excel_hash> <upload_reports>
+poetry run digitization_v2 --help
+```
+
+The current command for PDF validation is `validade-files-integrity`.
+
+### Example
+
+```bash
+poetry run digitization_v2 check-integrity -s "[122,123]" -u
 ```
 
 Parameters:
 
-- `target_excel_hash`: public CERNBox hash containing the inventory Excel files.
-- `upload_reports`: `0` to skip report upload, `1` to upload generated reports back to the S3 bucket. 
+- `-i, --inventory-source`: Inventory source. Supports CERNBOX Hash, range (`1..10`), or list (`[1,2]`).
+- `-u, --upload-reports`: Flag to upload validation reports back to the storage provider.
+- `-b, --bucket`: S3 bucket name (default: `digitization-dev`).
 
-### Example
+### Example without upload
 
 ```bash
-poetry run python refactory/main.py QslvWRIPsBcDAOK 0
+poetry run digitization_v2 check-integrity -s "[122,123]"
 ```
 
 ## Expected output
 
-The script generates:
+The CLI generates the same validation reports as the core pipeline:
 
-- `s3_pdf_issues.log` - text log with valid and corrupted files.
-- `s3_pdf_issues.json` - structured report with metadata, statistics, and file lists.
+- a text log file such as `s3_pdf_issues.log`
+- a structured JSON report with valid, corrupted, and missing file details
 
-If `upload_reports=1`, the reports are also uploaded back to the S3 bucket.
+If `-u` is provided, the reports will be uploaded back to the configured storage provider.
 
 ## Additional notes
 
-- If CERNBox upload requires authentication, provide `account` and `password` to `CernboxProvider`.
+- `CernboxProvider` reads optional credentials from environment variables:
+  - `CERNBOX_USER`
+  - `CERNBOX_PASSWORD`
+
+### Example environment variables for Cernbox
+
+```bash
+export CERNBOX_USER="your_username"
+export CERNBOX_PASSWORD="your_password"
+```
+
+- You may still pass `account` and `password` directly to `CernboxProvider` if preferred.
 - Use `test_connections.py` to verify connections before running the main pipeline.
diff --git a/refactory/cli.py b/refactory/cli.py
new file mode 100644
index 0000000..d5feb4b
--- /dev/null
+++ b/refactory/cli.py
@@ -0,0 +1,76 @@
+import click
+import ast
+from .main import run_validation_pipeline
+from storage_connection import S3Provider
+
+
+def parse_inventory(value):
+    """
+    Parses the input to identify if it's a literal list,
+    a range of IDs (1..10), or a single string/ID.
+    """
+    if value.isdigit():
+        return [int(value)]
+    if value.startswith("[") and value.endswith("]"):
+        try:
+            return ast.literal_eval(value)
+        except (ValueError, SyntaxError):
+            raise click.BadParameter("Invalid list format. Use '[1, 2, 3]'")
+
+    if ".." in value:
+        try:
+            start, end = map(int, value.split(".."))
+            return list(range(start, end + 1))
+        except ValueError:
+            pass
+    return value
+
+@click.group()
+def digitization_v2():
+    pass
+
+
+@digitization_v2.command("validate-files-integrity")
+@click.option(
+    "-s",
+    "--inventory-source",
+    required=True,
+    help="Target inventory. Supports a CERNBOX hash, range 1..10, or list [1,2].",
+)
+@click.option(
+    "-u",
+    "--upload-reports",
+    is_flag=True,
+    help="Upload validation reports back to the storage provider.",
+)
+@click.option(
+    "-b",
+    "--bucket",
+    default="digitization-dev",
+    show_default=True,
+    help="S3 Bucket name.",
+)
+def validate_files_integrity(inventory_source, upload_reports, bucket):
+    """
+    Validates files integrity and inventory alignment.
+    This command checks for corrupted files and missing boxes.
+    """
+
+    inventory_input = parse_inventory(inventory_source)
+    provider = S3Provider(bucket=bucket)
+
+    try:
+        run_validation_pipeline(
+            provider=provider,
+            base_path="cern-archives/raw/PDF/",
+            log_file="s3_pdf_issues.log",
+            inventory_source=inventory_input,
+            upload_reports=upload_reports,
+        )
+        click.echo("Process finished. Check the generated logs for details.")
+    except Exception as e:
+        click.secho(f"Error: {e}", fg="red", err=True)
+
+
+if __name__ == "__main__":
+    digitization_v2()
diff --git a/refactory/main.py b/refactory/main.py
index 9876cb3..665486d 100644
--- a/refactory/main.py
+++ b/refactory/main.py
@@ -3,6 +3,7 @@
 import os
 import sys
 import json
+from typing import Union
 from storage_connection import StorageProvider, S3Provider, CernboxProvider
 from validate_pdf import is_pdf_valid
 
@@ -11,21 +12,26 @@ def run_validation_pipeline(
     provider: StorageProvider,
     base_path: str,
     log_file: str,
-    target_excel_hash: str,
+    inventory_source: Union[str, list[int]],
     upload_reports: bool = False,
+
 ):
     """Navigates directories, validates files, and logs files status."""
-    inventory_provider = CernboxProvider(target_excel_hash)
-    excel_files = inventory_provider.list_excel("")
-
     target_box_numbers = set()
-    for file_path in excel_files:
-        filename = file_path.split(".")[0]
+    if isinstance(inventory_source, str):
+        inventory_provider = CernboxProvider(inventory_source)
+        excel_files = inventory_provider.list_excel("")
+
+        for file_path in excel_files:
+            filename = file_path.split(".")[0]
+
+            match = re.search(r"(?i:BOITE)[\-_]O0(\d+)(-\w+)?", filename)
 
-        match = re.search(r"(?i:BOITE)[\-_]O0(\d+)(-\w+)?", filename)
+            if match:
+                target_box_numbers.add(int(match.group(1)))
+    elif isinstance(inventory_source, list):
+        target_box_numbers = set(inventory_source)
 
-        if match:
-            target_box_numbers.add(int(match.group(1)))
     print(f"Excel files: {len(target_box_numbers)} boxes to check.")
 
     print(f"Folders in: {base_path}")
@@ -72,7 +78,7 @@ def run_validation_pipeline(
     missing_boxes = target_box_numbers - found_and_valid_boxes
 
     if missing_boxes:
-        print("\n🚨 Empty target boxes:")
+        print("\n Empty target boxes:")
         for box in sorted(missing_boxes):
             print(
                 f"  -> BOITE_O0{box}"
@@ -125,12 +131,11 @@ def run_validation_pipeline(
 
 if __name__ == "__main__":
     s3_provider = S3Provider(bucket="digitization-dev")
-    # cernbox_provider = CernboxProvider(public_link_hash="XjjFxUWUMpuTYCz")
 
     run_validation_pipeline(
         provider=s3_provider,  # cernbox_provider
         base_path="cern-archives/raw/PDF/",  # "teste/",
         log_file="s3_pdf_issues.log",
-        target_excel_hash=sys.argv[1],  # public_link_hash
-        upload_reports=int(sys.argv[2]),  # 0 | 1
+        inventory_source=sys.argv[1],  # public_link_hash
+        upload_reports=int(sys.argv[2])
     )
diff --git a/refactory/storage_connection.py b/refactory/storage_connection.py
index 6b48743..bdfdad9 100644
--- a/refactory/storage_connection.py
+++ b/refactory/storage_connection.py
@@ -17,7 +17,7 @@ def list_pdfs(self, folder_path: str) -> list[str]:
     @abstractmethod
     def download_to_temp(self, file_path: str, temp_file_path: str) -> None:
         pass
-        
+
     @abstractmethod
     def upload_file(self, local_file_path: str, remote_file_path: str) -> None:
         pass
@@ -56,34 +56,36 @@ def download_to_temp(self, file_path: str, temp_file_path: str) -> None:
 
     def upload_file(self, local_file_path: str, remote_file_path: str) -> None:
         self.s3.upload_file(local_file_path, self.bucket, remote_file_path)
-    
+
     def list_excel(self, folder_path: str) -> list[str]:
             response = self.s3.list_objects_v2(Bucket=self.bucket, Prefix=folder_path)
             return [
                 obj['Key'] for obj in response.get('Contents', [])
                 if obj['Key'].lower().endswith('.xlsx')
-            ]   
+            ]
 class CernboxProvider(StorageProvider):
-    def __init__(self, public_link_hash: str, account: str = None, password: str = None):
+    def __init__(self, public_link_hash: str):
         self.public_link_hash = public_link_hash
-        self.account = account
-        self.password = password
-        
+        self.account = os.getenv("CERNBOX_ACCOUNT")
+        self.password = os.getenv("CERNBOX_PASSWORD")
+
         self.public_base_url = f"https://cernbox.cern.ch/remote.php/dav/public-files/{public_link_hash}"
-        
-        if account:
-            self.auth_base_url = f"https://api.cernbox.cern.ch/remote.php/dav/files/{account}"
+
+        if self.account:
+            self.auth_base_url = f"https://api.cernbox.cern.ch/remote.php/dav/files/{self.account}"
+        else:
+            self.auth_base_url = None
 
     def _propfind(self, path: str, depth: str = "1") -> list[str]:
         url = f"{self.public_base_url}/{path}".rstrip('/') + '/'
         headers = {'Depth': depth}
-        
+
         response = requests.request('PROPFIND', url, headers=headers)
         response.raise_for_status()
 
         root = ET.fromstring(response.content)
         namespaces = {'d': 'DAV:'}
-        
+
         paths = []
         for response_tag in root.findall('d:response', namespaces)[1:]:
             href = response_tag.find('d:href', namespaces).text
@@ -114,11 +116,11 @@ def list_excel(self, folder_path: str)-> list[str]:
     def upload_file(self, local_file_path: str, remote_file_path: str) -> None:
         if not self.account or not self.password:
             raise ValueError("CERN account and password are required for uploading.")
-            
+
         clean_remote_path = remote_file_path.lstrip('/')
         url = f"{self.auth_base_url}/{clean_remote_path}"
-        
+
         with open(local_file_path, 'rb') as f:
             response = requests.put(url, data=f, auth=(self.account, self.password))
-            
+
         response.raise_for_status()
diff --git a/refactory/test_connections.py b/refactory/test_connections.py
index ad34e99..242f139 100644
--- a/refactory/test_connections.py
+++ b/refactory/test_connections.py
@@ -7,46 +7,31 @@ def test_s3():
     try:
         s3 = S3Provider(bucket="digitization-dev")
         base_path = "cern-archives/raw/PDF/"
-        
+
         folders = s3.list_folders(base_path)
         print("✅ Read: Success! Connected to S3.")
         print(f"Found {len(folders)} folders in '{base_path}'.")
 
-        ### Test Upload
-        
-        # print("\n--- Testing S3 Upload ---")
-        # remote_test_file = f"{base_path}upload_test_s3.txt"
-        
-        # with tempfile.NamedTemporaryFile(delete=False, mode='w', encoding='utf-8') as tmp:
-        #     tmp.write("Upload test file generated by test_connections.py")
-        #     tmp_path = tmp.name
-            
-        # try:
-        #     s3.upload_file(tmp_path, remote_test_file)
-        #     print(f"✅ Write: Success! File sent to: {remote_test_file}")
-        # finally:
-        #     os.remove(tmp_path) 
-            
     except Exception as e:
         print("❌ Failed to connect/operate on S3.")
         print(f"Details: {e}")
 
 def test_cernbox():
     print("\n--- Testing CERNBOX connection (Hybrid Mode) ---")
-    
+
     # 1. Read Variables (Public)
     public_hash = "QslvWRIPsBcDAOK"
     read_base_path = "" # Relative path inside the public link
-    
+
     # 2. Write Variables (Private/Authenticated)
     cern_user = "gadesant" # CERN username
     cern_password = os.environ.get("CERNBOX_PASSWORD")
     write_base_path = "eos/user/g/gadesant/teste/"#"eos/user/{u}/{user}/teste/"
-    
+
     if public_hash == "PUT_YOUR_PUBLIC_HASH_HERE":
         print("Warning: Configure the public_hash in the code before testing.")
         return
-        
+
     if not cern_password:
         print("❌ The CERNBOX_PASSWORD environment variable is not set.")
         print("Run in terminal: export CERNBOX_PASSWORD='your_password'")
@@ -55,26 +40,17 @@ def test_cernbox():
     try:
         # Passing all three arguments
         cernbox = CernboxProvider(public_link_hash=public_hash, account=cern_user, password=cern_password)
-        
+
         print("\n[Phase 1: Reading from Public Link]")
         folders = cernbox.list_folders(read_base_path)
         print("✅ Read: Success (Anonymous)!")
         print(f"Found {len(folders)} items at the root of the link.")
-        
+
         print("\n[Phase 2: Writing via Authenticated WebDAV]")
-        remote_test_file = f"{write_base_path}hybrid_connection_test.txt"
-        
+
         with tempfile.NamedTemporaryFile(delete=False, mode='w', encoding='utf-8') as tmp:
             tmp.write("Authenticated upload from test_connections.py")
-            tmp_path = tmp.name
 
-        ### Test Upload
-        # try:
-        #     cernbox.upload_file(tmp_path, remote_test_file)
-        #     print(f"✅ Write: Success (Authenticated)! File sent to: {remote_test_file}")
-        # finally:
-        #     os.remove(tmp_path)
-            
     except Exception as e:
         print("❌ Failed to connect/operate on CERNBOX.")
         print(f"Details: {e}")
diff --git a/requirements.txt b/requirements.txt
index d9af537..8d71172 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,3 +1,3 @@
-boto3
-requests
-pypdf
\ No newline at end of file
+boto3>=1.38.9,<2.0.0
+requests>=2.0.0,<3.0.0
+pypdf>=3.0.0,<7.0.0