add bedesten module
This commit is contained in:
saidsurucu
@@ -0,0 +1 @@
|
||||
# bedesten_mcp_module/__init__.py
|
||||
@@ -0,0 +1,183 @@
|
||||
# bedesten_mcp_module/client.py
|
||||
|
||||
import httpx
|
||||
import base64
|
||||
from typing import Optional
|
||||
import logging
|
||||
from markitdown import MarkItDown
|
||||
import tempfile
|
||||
import os
|
||||
|
||||
from .models import (
|
||||
BedestenSearchRequest, BedestenSearchResponse,
|
||||
BedestenDocumentRequest, BedestenDocumentResponse,
|
||||
BedestenDocumentMarkdown, BedestenDocumentRequestData
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class BedestenApiClient:
|
||||
"""
|
||||
API Client for Bedesten (bedesten.adalet.gov.tr) - Alternative legal decision search system.
|
||||
Currently used for Yargıtay decisions, but can be extended for other court types.
|
||||
"""
|
||||
BASE_URL = "https://bedesten.adalet.gov.tr"
|
||||
SEARCH_ENDPOINT = "/emsal-karar/searchDocuments"
|
||||
DOCUMENT_ENDPOINT = "/emsal-karar/getDocumentContent"
|
||||
|
||||
def __init__(self, request_timeout: float = 60.0):
|
||||
self.http_client = httpx.AsyncClient(
|
||||
base_url=self.BASE_URL,
|
||||
headers={
|
||||
"Accept": "*/*",
|
||||
"Accept-Language": "tr-TR,tr;q=0.9,en-US;q=0.8,en;q=0.7",
|
||||
"AdaletApplicationName": "UyapMevzuat",
|
||||
"Content-Type": "application/json; charset=utf-8",
|
||||
"Origin": "https://mevzuat.adalet.gov.tr",
|
||||
"Referer": "https://mevzuat.adalet.gov.tr/",
|
||||
"Sec-Fetch-Dest": "empty",
|
||||
"Sec-Fetch-Mode": "cors",
|
||||
"Sec-Fetch-Site": "same-site",
|
||||
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36"
|
||||
},
|
||||
timeout=request_timeout
|
||||
)
|
||||
|
||||
async def search_documents(self, search_request: BedestenSearchRequest) -> BedestenSearchResponse:
|
||||
"""
|
||||
Search for documents using Bedesten API.
|
||||
Currently supports: YARGITAYKARARI, DANISTAYKARARI, YERELHUKMAHKARARI, etc.
|
||||
"""
|
||||
logger.info(f"BedestenApiClient: Searching documents with phrase: {search_request.data.phrase}")
|
||||
|
||||
try:
|
||||
response = await self.http_client.post(
|
||||
self.SEARCH_ENDPOINT,
|
||||
json=search_request.model_dump()
|
||||
)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
|
||||
# Parse and return the response
|
||||
return BedestenSearchResponse(**response_json)
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"BedestenApiClient: HTTP request error during search: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"BedestenApiClient: Error processing search response: {e}")
|
||||
raise
|
||||
|
||||
async def get_document_as_markdown(self, document_id: str) -> BedestenDocumentMarkdown:
|
||||
"""
|
||||
Get document content and convert to markdown.
|
||||
Handles both HTML (text/html) and PDF (application/pdf) content types.
|
||||
"""
|
||||
logger.info(f"BedestenApiClient: Fetching document for markdown conversion (ID: {document_id})")
|
||||
|
||||
try:
|
||||
# Prepare request
|
||||
doc_request = BedestenDocumentRequest(
|
||||
data=BedestenDocumentRequestData(documentId=document_id)
|
||||
)
|
||||
|
||||
# Get document
|
||||
response = await self.http_client.post(
|
||||
self.DOCUMENT_ENDPOINT,
|
||||
json=doc_request.model_dump()
|
||||
)
|
||||
response.raise_for_status()
|
||||
response_json = response.json()
|
||||
doc_response = BedestenDocumentResponse(**response_json)
|
||||
|
||||
# Decode base64 content
|
||||
content_bytes = base64.b64decode(doc_response.data.content)
|
||||
mime_type = doc_response.data.mimeType
|
||||
|
||||
logger.info(f"BedestenApiClient: Document mime type: {mime_type}")
|
||||
|
||||
# Convert to markdown based on mime type
|
||||
if mime_type == "text/html":
|
||||
html_content = content_bytes.decode('utf-8')
|
||||
markdown_content = self._convert_html_to_markdown(html_content)
|
||||
elif mime_type == "application/pdf":
|
||||
markdown_content = self._convert_pdf_to_markdown(content_bytes)
|
||||
else:
|
||||
logger.warning(f"Unsupported mime type: {mime_type}")
|
||||
markdown_content = f"Unsupported content type: {mime_type}. Unable to convert to markdown."
|
||||
|
||||
return BedestenDocumentMarkdown(
|
||||
documentId=document_id,
|
||||
markdown_content=markdown_content,
|
||||
source_url=f"{self.BASE_URL}/document/{document_id}",
|
||||
mime_type=mime_type
|
||||
)
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"BedestenApiClient: HTTP error fetching document {document_id}: {e}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"BedestenApiClient: Error processing document {document_id}: {e}")
|
||||
raise
|
||||
|
||||
def _convert_html_to_markdown(self, html_content: str) -> Optional[str]:
|
||||
"""Convert HTML to Markdown using MarkItDown"""
|
||||
if not html_content:
|
||||
return None
|
||||
|
||||
temp_file_path = None
|
||||
try:
|
||||
md_converter = MarkItDown()
|
||||
|
||||
# Write HTML to temp file
|
||||
with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".html", encoding="utf-8") as tmp:
|
||||
tmp.write(html_content)
|
||||
temp_file_path = tmp.name
|
||||
|
||||
# Convert
|
||||
result = md_converter.convert(temp_file_path)
|
||||
markdown_content = result.text_content
|
||||
|
||||
logger.info("Successfully converted HTML to Markdown")
|
||||
return markdown_content
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error converting HTML to Markdown: {e}")
|
||||
return f"Error converting HTML content: {str(e)}"
|
||||
finally:
|
||||
if temp_file_path and os.path.exists(temp_file_path):
|
||||
os.remove(temp_file_path)
|
||||
|
||||
def _convert_pdf_to_markdown(self, pdf_bytes: bytes) -> Optional[str]:
|
||||
"""Convert PDF to Markdown using MarkItDown"""
|
||||
if not pdf_bytes:
|
||||
return None
|
||||
|
||||
temp_file_path = None
|
||||
try:
|
||||
# MarkItDown supports PDF with markitdown[pdf]
|
||||
md_converter = MarkItDown()
|
||||
|
||||
# Write PDF to temp file
|
||||
with tempfile.NamedTemporaryFile(mode="wb", delete=False, suffix=".pdf") as tmp:
|
||||
tmp.write(pdf_bytes)
|
||||
temp_file_path = tmp.name
|
||||
|
||||
# Convert
|
||||
result = md_converter.convert(temp_file_path)
|
||||
markdown_content = result.text_content
|
||||
|
||||
logger.info("Successfully converted PDF to Markdown")
|
||||
return markdown_content
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error converting PDF to Markdown: {e}")
|
||||
return f"Error converting PDF content: {str(e)}. The document may be corrupted or in an unsupported format."
|
||||
finally:
|
||||
if temp_file_path and os.path.exists(temp_file_path):
|
||||
os.remove(temp_file_path)
|
||||
|
||||
async def close_client_session(self):
|
||||
"""Close HTTP client session"""
|
||||
await self.http_client.aclose()
|
||||
logger.info("BedestenApiClient: HTTP client session closed.")
|
||||
@@ -0,0 +1,115 @@
|
||||
# bedesten_mcp_module/models.py
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from typing import List, Optional, Dict, Any, Literal, Union
|
||||
|
||||
# Import YargitayBirimEnum for chamber filtering
|
||||
from yargitay_mcp_module.models import YargitayBirimEnum
|
||||
|
||||
# Danıştay Chamber/Board Options
|
||||
DanistayBirimEnum = Literal[
|
||||
"", # Empty string for "All" chambers
|
||||
# Main Councils
|
||||
"Büyük Gen.Kur.", # Grand General Assembly
|
||||
"İdare Dava Daireleri Kurulu", # Administrative Cases Chambers Council
|
||||
"Vergi Dava Daireleri Kurulu", # Tax Cases Chambers Council
|
||||
"İçtihatları Birleştirme Kurulu", # Precedents Unification Council
|
||||
"İdari İşler Kurulu", # Administrative Affairs Council
|
||||
"Başkanlar Kurulu", # Presidents Council
|
||||
# Chambers
|
||||
"1. Daire", "2. Daire", "3. Daire", "4. Daire", "5. Daire",
|
||||
"6. Daire", "7. Daire", "8. Daire", "9. Daire", "10. Daire",
|
||||
"11. Daire", "12. Daire", "13. Daire", "14. Daire", "15. Daire",
|
||||
"16. Daire", "17. Daire",
|
||||
# Military High Administrative Court
|
||||
"Askeri Yüksek İdare Mahkemesi",
|
||||
"Askeri Yüksek İdare Mahkemesi Daireler Kurulu",
|
||||
"Askeri Yüksek İdare Mahkemesi Başsavcılığı",
|
||||
"Askeri Yüksek İdare Mahkemesi 1. Daire",
|
||||
"Askeri Yüksek İdare Mahkemesi 2. Daire",
|
||||
"Askeri Yüksek İdare Mahkemesi 3. Daire"
|
||||
]
|
||||
|
||||
# Search Request Models
|
||||
class BedestenSearchData(BaseModel):
|
||||
pageSize: int
|
||||
pageNumber: int
|
||||
itemTypeList: List[str]
|
||||
phrase: str
|
||||
birimAdi: Optional[Union[YargitayBirimEnum, DanistayBirimEnum]] = Field(None, description="""
|
||||
Chamber/Board filter (optional). Available options depend on itemTypeList:
|
||||
|
||||
For YARGITAYKARARI (52 options):
|
||||
- None/null for ALL chambers
|
||||
- 'Hukuk Genel Kurulu', '1. Hukuk Dairesi' through '23. Hukuk Dairesi'
|
||||
- 'Ceza Genel Kurulu', '1. Ceza Dairesi' through '23. Ceza Dairesi'
|
||||
- 'Hukuk Daireleri Başkanlar Kurulu', 'Ceza Daireleri Başkanlar Kurulu'
|
||||
- 'Büyük Genel Kurulu'
|
||||
|
||||
For DANISTAYKARAR (27 options):
|
||||
- None/null for ALL chambers
|
||||
- 'Büyük Gen.Kur.', 'İdare Dava Daireleri Kurulu', 'Vergi Dava Daireleri Kurulu'
|
||||
- '1. Daire' through '17. Daire'
|
||||
- 'İçtihatları Birleştirme Kurulu', 'İdari İşler Kurulu', 'Başkanlar Kurulu'
|
||||
- Military courts: 'Askeri Yüksek İdare Mahkemesi' variants
|
||||
""")
|
||||
sortFields: List[str] = ["KARAR_TARIHI"]
|
||||
sortDirection: str = "desc"
|
||||
|
||||
class BedestenSearchRequest(BaseModel):
|
||||
data: BedestenSearchData
|
||||
applicationName: str = "UyapMevzuat"
|
||||
paging: bool = True
|
||||
|
||||
# Search Response Models
|
||||
class BedestenItemType(BaseModel):
|
||||
name: str
|
||||
description: str
|
||||
|
||||
class BedestenDecisionEntry(BaseModel):
|
||||
documentId: str
|
||||
itemType: BedestenItemType
|
||||
birimId: Optional[str] = None
|
||||
birimAdi: Optional[str]
|
||||
esasNoYil: int
|
||||
esasNoSira: int
|
||||
kararNoYil: int
|
||||
kararNoSira: int
|
||||
kararTuru: Optional[str] = None
|
||||
kararTarihi: str
|
||||
kararTarihiStr: str
|
||||
kesinlesmeDurumu: Optional[str] = None
|
||||
kararNo: str
|
||||
esasNo: str
|
||||
|
||||
class BedestenSearchDataResponse(BaseModel):
|
||||
emsalKararList: List[BedestenDecisionEntry]
|
||||
total: int
|
||||
start: int
|
||||
|
||||
class BedestenSearchResponse(BaseModel):
|
||||
data: BedestenSearchDataResponse
|
||||
metadata: Dict[str, Any]
|
||||
|
||||
# Document Request/Response Models
|
||||
class BedestenDocumentRequestData(BaseModel):
|
||||
documentId: str
|
||||
|
||||
class BedestenDocumentRequest(BaseModel):
|
||||
data: BedestenDocumentRequestData
|
||||
applicationName: str = "UyapMevzuat"
|
||||
|
||||
class BedestenDocumentData(BaseModel):
|
||||
content: str # Base64 encoded HTML or PDF
|
||||
mimeType: str
|
||||
version: int
|
||||
|
||||
class BedestenDocumentResponse(BaseModel):
|
||||
data: BedestenDocumentData
|
||||
metadata: Dict[str, Any]
|
||||
|
||||
class BedestenDocumentMarkdown(BaseModel):
|
||||
documentId: str = Field(..., description="The document ID from Bedesten")
|
||||
markdown_content: Optional[str] = Field(None, description="The decision content converted to Markdown")
|
||||
source_url: str = Field(..., description="The source URL of the document")
|
||||
mime_type: Optional[str] = Field(None, description="Original content type (text/html or application/pdf)")
|
||||
Reference in New Issue
Block a user