datamule 1.0.2__py3-none-any.whl → 1.0.6__py3-none-any.whl

datamule/mulebot/tools.py

@@ -1,82 +0,0 @@
-
-get_company_concept_tool = {
-        "type": "function",
-        "function": {
-            "name": "get_company_concept",
-            "description": "ONLY use this when explicitly asked to get company XBRL concepts or facts for a given ticker",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "ticker": {"type": "string", "description": "The ticker of the company to get facts for"}
-                },
-                "required": ["ticker"]
-            }
-        }
-    }
-
-identifier_to_cik_tool =     {
-        "type": "function",
-        "function": {
-            "name": "identifier_to_cik",
-            "description": "ONLY use this when explicitly asked to convert a company's ticker to a CIK.",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "ticker": {"type": "string", "description": "The ticker to convert to a CIK"},
-                },
-                "required": ["ticker"]
-            }
-        }
-    }
-
-get_filing_urls_tool = {
-    "type": "function",
-    "function": {
-        "name": "get_filing_urls",
-        "description": "ONLY use this when explicitly asked to get URLs of filings for a given company or multiple",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "ticker": {"type": "string", "description": "Ticker symbol of the company. Can be a single ticker or a list of tickers."},
-                "form": {"type": "string", "description": "Form type to get (e.g., '10-K', '10-Q')"},
-                "date": {"type": "string", "description": "Date of the filing, can be a single date, a range, or a list of dates. Format: 'YYYY-MM-DD'. If range use a tuple of two dates."},
-            },
-            "required": ["ticker"]
-        }
-    }
-}
-
-find_filing_section_by_title_tool = {
-    "type": "function",
-    "function": {
-        "name": "find_filing_section_by_title",
-        "description": "ONLY use this when explicitly given a filing URL and told to find a specific section",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "url": {"type": "string", "description": "URL of the filing to parse"},
-                "title": {"type": "string", "description": "The section title to search for in the filing"}
-            },
-            "required": ["url","title"]
-        }
-    }
-}
-
-return_title_tool = {
-    "type": "function",
-    "function": {
-        "name": "return_title",
-        "description": "use this to select a title",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "title": {"type": "string", "description": "The title to return"}
-            },
-            "required": ["title"]
-        }
-    }
-}
-
-
-
-tools = [get_company_concept_tool, identifier_to_cik_tool, get_filing_urls_tool, find_filing_section_by_title_tool]

datamule/packageupdater.py

@@ -1,207 +0,0 @@
-import asyncio
-import aiohttp
-import json
-import csv
-import os
-from pkg_resources import resource_filename
-from .helper import headers
-from .downloader.downloader import PreciseRateLimiter, RateMonitor
-
-class PackageUpdater:
-    def __init__(self):
-        self.limiter = PreciseRateLimiter(5)  # 5 requests per second
-        self.rate_monitor = RateMonitor()
-        self.headers = headers
-    
-    async def _fetch_json(self, session, url):
-        """Fetch JSON with rate limiting and monitoring."""
-        async with self.limiter:
-            try:
-                async with session.get(url) as response:
-                    response.raise_for_status()
-                    content = await response.read()
-                    await self.rate_monitor.add_request(len(content))
-                    return await response.json()
-            except Exception as e:
-                print(f"Error fetching {url}: {str(e)}")
-                return None
-
-    async def _update_company_tickers(self):
-        """Update company tickers data files."""
-        url = 'https://www.sec.gov/files/company_tickers.json'
-        
-        # Define file paths
-        json_file = resource_filename('datamule', 'data/company_tickers.json')
-        csv_file = resource_filename('datamule', 'data/company_tickers.csv')
-        
-        # Define temporary file paths
-        temp_json_file = json_file + '.temp'
-        temp_csv_file = csv_file + '.temp'
-
-        async with aiohttp.ClientSession(headers=self.headers) as session:
-            try:
-                data = await self._fetch_json(session, url)
-                if not data:
-                    raise Exception("Failed to fetch company tickers data")
-
-                # Save the raw JSON file
-                with open(temp_json_file, 'w') as f:
-                    json.dump(data, f, indent=4)
-                
-                # Convert to CSV
-                with open(temp_csv_file, 'w', newline='') as csvfile:
-                    fieldnames = ['cik', 'ticker', 'title']
-                    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
-                    writer.writeheader()
-                    for _, company in data.items():
-                        writer.writerow({
-                            'cik': str(company['cik_str']).zfill(10),
-                            'ticker': company['ticker'],
-                            'title': company['title']
-                        })
-
-                # Replace original files
-                for src, dst in [(temp_json_file, json_file), (temp_csv_file, csv_file)]:
-                    if os.path.exists(dst):
-                        os.remove(dst)
-                    os.rename(src, dst)
-
-                print(f"Company tickers successfully updated")
-                return True
-
-            except Exception as e:
-                print(f"Error updating company tickers: {str(e)}")
-                return False
-            
-            finally:
-                # Clean up temp files
-                for temp_file in [temp_json_file, temp_csv_file]:
-                    if os.path.exists(temp_file):
-                        try:
-                            os.remove(temp_file)
-                        except Exception as e:
-                            print(f"Warning: Could not remove {temp_file}: {str(e)}")
-
-    async def _process_metadata_batch(self, session, companies, metadata_writer, former_names_writer):
-        """Process a batch of companies for metadata updates."""
-        metadata_fields = [
-            'cik', 'name', 'entityType', 'sic', 'sicDescription', 'ownerOrg',
-            'insiderTransactionForOwnerExists', 'insiderTransactionForIssuerExists',
-            'tickers', 'exchanges', 'ein', 'description', 'website', 'investorWebsite',
-            'category', 'fiscalYearEnd', 'stateOfIncorporation', 'stateOfIncorporationDescription',
-            'phone', 'flags', 'mailing_street1', 'mailing_street2', 'mailing_city',
-            'mailing_stateOrCountry', 'mailing_zipCode', 'mailing_stateOrCountryDescription',
-            'business_street1', 'business_street2', 'business_city', 'business_stateOrCountry',
-            'business_zipCode', 'business_stateOrCountryDescription'
-        ]
-
-        tasks = []
-        for company in companies:
-            cik = company['cik']
-            url = f'https://data.sec.gov/submissions/CIK{str(cik).zfill(10)}.json'
-            tasks.append(self._fetch_json(session, url))
-
-        results = await asyncio.gather(*tasks, return_exceptions=True)
-
-        for company, result in zip(companies, results):
-            if isinstance(result, Exception) or not result:
-                print(f"Error processing CIK {company['cik']}: {str(result) if isinstance(result, Exception) else 'No data'}")
-                continue
-
-            try:
-                metadata = {field: result.get(field, '') for field in metadata_fields if field not in ['tickers', 'exchanges']}
-                metadata['cik'] = company['cik']
-                metadata['tickers'] = ','.join(result.get('tickers', []))
-                metadata['exchanges'] = ','.join(result.get('exchanges', []))
-
-                # Add address information
-                for address_type in ['mailing', 'business']:
-                    address = result.get('addresses', {}).get(address_type, {})
-                    for key, value in address.items():
-                        metadata[f'{address_type}_{key}'] = value if value is not None else ''
-
-                metadata_writer.writerow(metadata)
-
-                for former_name in result.get('formerNames', []):
-                    former_names_writer.writerow({
-                        'cik': company['cik'],
-                        'former_name': former_name['name'],
-                        'from_date': former_name['from'],
-                        'to_date': former_name['to']
-                    })
-
-            except Exception as e:
-                print(f"Error processing metadata for CIK {company['cik']}: {str(e)}")
-
-    async def _update_company_metadata(self):
-        """Update company metadata and former names files."""
-        metadata_file = resource_filename('datamule', 'data/company_metadata.csv')
-        former_names_file = resource_filename('datamule', 'data/company_former_names.csv')
-        
-        temp_metadata_file = metadata_file + '.temp'
-        temp_former_names_file = former_names_file + '.temp'
-
-        # Load current company tickers
-        with open(resource_filename('datamule', 'data/company_tickers.csv'), 'r') as f:
-            company_tickers = list(csv.DictReader(f))
-
-        metadata_fields = ['cik', 'name', 'entityType', 'sic', 'sicDescription', 'ownerOrg',
-                        'insiderTransactionForOwnerExists', 'insiderTransactionForIssuerExists',
-                        'tickers', 'exchanges', 'ein', 'description', 'website', 'investorWebsite',
-                        'category', 'fiscalYearEnd', 'stateOfIncorporation', 'stateOfIncorporationDescription',
-                        'phone', 'flags', 'mailing_street1', 'mailing_street2', 'mailing_city',
-                        'mailing_stateOrCountry', 'mailing_zipCode', 'mailing_stateOrCountryDescription',
-                        'business_street1', 'business_street2', 'business_city', 'business_stateOrCountry',
-                        'business_zipCode', 'business_stateOrCountryDescription']
-
-        former_names_fields = ['cik', 'former_name', 'from_date', 'to_date']
-
-        try:
-            async with aiohttp.ClientSession(headers=self.headers) as session:
-                with open(temp_metadata_file, 'w', newline='') as mf, \
-                     open(temp_former_names_file, 'w', newline='') as fnf:
-                    
-                    metadata_writer = csv.DictWriter(mf, fieldnames=metadata_fields)
-                    metadata_writer.writeheader()
-                    
-                    former_names_writer = csv.DictWriter(fnf, fieldnames=former_names_fields)
-                    former_names_writer.writeheader()
-
-                    # Process in batches of 10 companies
-                    batch_size = 10
-                    for i in range(0, len(company_tickers), batch_size):
-                        batch = company_tickers[i:i + batch_size]
-                        await self._process_metadata_batch(
-                            session, batch, metadata_writer, former_names_writer
-                        )
-
-            # Replace original files
-            for src, dst in [(temp_metadata_file, metadata_file), 
-                           (temp_former_names_file, former_names_file)]:
-                if os.path.exists(dst):
-                    os.remove(dst)
-                os.rename(src, dst)
-
-            print("Company metadata successfully updated")
-            return True
-
-        except Exception as e:
-            print(f"Error updating company metadata: {str(e)}")
-            return False
-
-        finally:
-            # Clean up temp files
-            for temp_file in [temp_metadata_file, temp_former_names_file]:
-                if os.path.exists(temp_file):
-                    try:
-                        os.remove(temp_file)
-                    except Exception as e:
-                        print(f"Warning: Could not remove {temp_file}: {str(e)}")
-
-    def update_company_tickers(self):
-        """Update company tickers data files."""
-        return asyncio.run(self._update_company_tickers())
-
-    def update_company_metadata(self):
-        """Update company metadata and former names files."""
-        return asyncio.run(self._update_company_metadata())

datamule-1.0.2.dist-info/RECORD

@@ -1,43 +0,0 @@
-datamule/__init__.py,sha256=IDVK3i5i5DxLlQJ_71aYkloGNi528JOUx8hU6bDzLXM,1255
-datamule/config.py,sha256=Y--CVv7JcgrjJkMOSLrvm2S8B9ost6RMSkGviP-MKtg,883
-datamule/document.py,sha256=-XT3nkRb1oCOken7n3AUCI8itQNfuKVN86cuD3rys3E,10912
-datamule/helper.py,sha256=tr3AQWus9dHNZFKpLSglWjcb8zmm5qDXjOWACMhvMxQ,4594
-datamule/monitor.py,sha256=AfhGqC_GFTYWemRKgYE85V7rIGMN_pbcpxW6kORQtpw,9273
-datamule/packageupdater.py,sha256=vEGqlTj6FudIeVHBVJltPh2eBDEqMG9HYmnyrRVKeSU,9595
-datamule/portfolio.py,sha256=U_QRNk_CbMmi3nJ0VBIwc9SVEGq6kA8LCZHBj9nOGXs,4032
-datamule/submission.py,sha256=uioIYJbsoe-87nRPyzlo-LZ8Hp7HG7A4KPGSnw86PKY,2790
-datamule/book/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datamule/book/book.py,sha256=ns7wVk_gLX5KhAghnSTxKcWIB8bKg7pwsM3es5GfCyM,1422
-datamule/book/eftsquery.py,sha256=MW-rMb3L-S1sgAR_Y-Ca3zGa1W9hclTzH52twUK87oM,4596
-datamule/book/xbrl_retriever.py,sha256=qLzrskqrQ8guEMFudlUCWFvRqAgSthhql5FXh_E3eCo,2910
-datamule/data/company_former_names.csv,sha256=HE9cAv-_QKFX6jT-_-D0rHmaDyQuAzL4MJwank5O1U8,706380
-datamule/data/company_metadata.csv,sha256=yPovrCVjYwLWTU_hBUFJymp8iNO0NBYuq_QwOkRLoN8,3068599
-datamule/data/company_tickers.csv,sha256=GW6lOP54RiGJCx-d9N5jEBy7tGVgU3zI-5xHJXrZfSI,400363
-datamule/data/sec-glossary.csv,sha256=-cN7GjiadLw5C1sv4zSeCnfeZZDYeSgJl-0ydarMAo0,251209
-datamule/data/xbrl_descriptions.csv,sha256=SQ9wUURNqG424rnTiZtopsxV2q-PvU4NMj52LqgDsvg,2621524
-datamule/downloader/downloader.py,sha256=vnMsw0oWqRa84scu6ZcywxbJxsIn38vLV0tybakx3jQ,15217
-datamule/downloader/premiumdownloader.py,sha256=YhGFwkYqjLkdc5ex2YKM-L7nBAPm5MMCdTwVVP0JO78,14314
-datamule/mapping_dicts/txt_mapping_dicts.py,sha256=Eh6qYhseuKjjnxGh0A5blHr7mbq9CigFn6Zv9xcG2zU,5783
-datamule/mapping_dicts/xml_mapping_dicts.py,sha256=Z22yDVwKYonUfM5foQP00dVDE8EHhhMKp0CLqVKV5OI,438
-datamule/mulebot/__init__.py,sha256=YvZXV6xQ0iP-oGD8rloufjdwJL6D46P3NNr0CY9PQCA,29
-datamule/mulebot/helper.py,sha256=olztOwltfELZ-IERM2bRNLBavD04kfB6ueWTisJAleA,1080
-datamule/mulebot/mulebot.py,sha256=XbtgvXBSFu9OaaLW_k1KDgHVTNQGV8_0ZwNMFad-pPU,5837
-datamule/mulebot/search.py,sha256=mwvbB6Fex5dEQkfxkCL53ne5pXdVno-5KlZ5vZyGnJQ,2073
-datamule/mulebot/tools.py,sha256=ctnGc2HItR-Roi-QXkc7GEaAOEYQiFRtfmdmIxNxYXk,2940
-datamule/mulebot/mulebot_server/__init__.py,sha256=x1QhXys7BWxi2g9_ZHUYA6S6rL3VL2718x4rYtGaaIg,33
-datamule/mulebot/mulebot_server/server.py,sha256=M7kU4aZUoi8X8DUKZNckLewBiI637Krbeap31qD2jt8,3547
-datamule/mulebot/mulebot_server/static/css/minimalist.css,sha256=Tz1tz8oF_esbfCvLTJBmTfb-5MIiqjfhU_4A4nto1mo,2974
-datamule/mulebot/mulebot_server/static/scripts/artifacts.js,sha256=WUAoI3LtEBEt3x-Ri0gwd6YT0JtGNwDZ_b8tuhWWSsg,2258
-datamule/mulebot/mulebot_server/static/scripts/chat.js,sha256=q8vV_KtzuNCXCfXqavM1HROIkYHItOAmaR8P1OjSqa0,3108
-datamule/mulebot/mulebot_server/static/scripts/filingArtifacts.js,sha256=wxeIM2RzF6Zh_9ivnYuNyTzIgIcEz0-zX8gTCvyACJo,2034
-datamule/mulebot/mulebot_server/static/scripts/listArtifacts.js,sha256=DZFLe-45mmzWvJPO1be5Ivfqx0BInrXfduQ1IhbHWzk,429
-datamule/mulebot/mulebot_server/static/scripts/main.js,sha256=NEIVih1WJeQ-qo5k8hnmgFHd7N839Mr6hJur856oXVQ,1882
-datamule/mulebot/mulebot_server/static/scripts/prefilledPrompt.js,sha256=mGhAXQnjnSxYqVqg1mE5g_ev0-aDhh849xunQtRchnY,1093
-datamule/mulebot/mulebot_server/static/scripts/suggestions.js,sha256=TCyz8OYuXeIG9qNRgwU2fhz18YNXpy4Bl9mk66lXefo,1795
-datamule/mulebot/mulebot_server/static/scripts/tableArtifacts.js,sha256=UtkUpLvELNI4Ibpb7VstgVA9Tk-8jbkxXhmXsgufFa4,4437
-datamule/mulebot/mulebot_server/static/scripts/utils.js,sha256=oGPMtyT9dvuqHqrfZj33t4vLZiF8UJrMXB1hpPXRNu4,1255
-datamule/mulebot/mulebot_server/templates/chat-minimalist.html,sha256=MsTbgpnLD0JCQiKKP3XeeNJRNsRqKsRa1j_XXW7nBKw,6975
-datamule-1.0.2.dist-info/METADATA,sha256=GF3kWzUe2GxJjJwRyewMfLh8intVCMZuSIngk6o1J4g,732
-datamule-1.0.2.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-datamule-1.0.2.dist-info/top_level.txt,sha256=iOfgmtSMFVyr7JGl_bYSTDry79JbmsG4p8zKq89ktKk,9
-datamule-1.0.2.dist-info/RECORD,,