refactor(teddi-mcp): remove dead code from CLI, client, and models (7fbb8964) · Commits · Jan Reimes / 3gpp-crawler

src/teddi-mcp/teddi_mcp/args.py

+5 −5

Original line number	Diff line number	Diff line
		@@ -6,11 +6,11 @@ import typer

		from teddi_mcp.models import OutputFormat, SearchIn, SearchPattern

		TermArgument = Annotated[
		_ = Annotated[
		str,
		typer.Argument(..., help="Term to search for"),
		]
		SearchInOption = Annotated[
		_ = Annotated[
		SearchIn,
		typer.Option(
		SearchIn.BOTH,
		@@ -18,7 +18,7 @@ SearchInOption = Annotated[
		help="Search scope: abbreviations, definitions, or both",
		),
		]
		SearchPatternOption = Annotated[
		_ = Annotated[
		SearchPattern,
		typer.Option(
		SearchPattern.ALL_OCCURRENCES,
		@@ -26,7 +26,7 @@ SearchPatternOption = Annotated[
		help="Pattern matching: exactmatch, startingwith, endingwith, alloccurrences. Default: alloccurrences",
		),
		]
		TechnicalBodiesOption = Annotated[
		_ = Annotated[
		str \| None,
		typer.Option(
		None,
		@@ -34,7 +34,7 @@ TechnicalBodiesOption = Annotated[
		help="Comma-separated TB names to filter by (e.g., '3gpp,etsi'). Default: all",
		),
		]
		OutputFormatOption = Annotated[
		_ = Annotated[
		OutputFormat,
		typer.Option(
		OutputFormat.TABLE,

src/teddi-mcp/teddi_mcp/cli.py

+1 −142

Original line number	Diff line number	Diff line
		"""Typer CLI for TEDDI search (non-MCP interface)."""

		import asyncio
		import json
		import logging
		from collections.abc import Callable
		from functools import wraps
		from typing import Annotated, Any
		from typing import Any

		import typer
		from rich.console import Console
		from rich.table import Table

		from teddi_mcp.client import TeddiClient
		from teddi_mcp.models import (
		OutputFormat,
		SearchIn,
		SearchPattern,
		SearchRequest,
		SearchResponse,
		TechnicalBody,
		)

		app = typer.Typer(help="TEDDI CLI - search and MCP server")
		@@ -33,16 +26,6 @@ logging.basicConfig(
		)


		def async_command(func: Callable[..., Any]) -> Callable[..., Any]:
		"""Decorator to run async functions in typer commands."""

		@wraps(func)
		def wrapper(args: Any, *kwargs: Any) -> Any:
		return asyncio.run(func(args, *kwargs))

		return wrapper


		def _build_results_payload(request: SearchRequest, response: SearchResponse) -> dict[str, Any]:
		"""Build canonical machine-readable payload for non-table outputs."""
		return {
		@@ -134,130 +117,6 @@ def _render_table(term: str, response: SearchResponse) -> None:
		console.print(table)


		@search_app.command("term")
		@async_command
		async def search_term(
		term: Annotated[
		str,
		typer.Argument(..., help="Term to search for"),
		],
		search_in: Annotated[
		str,
		typer.Option(
		help="Search scope: abbreviations, definitions, or both",
		),
		] = "both",
		search_pattern: Annotated[
		str,
		typer.Option(
		help="Pattern matching: exactmatch, startingwith, endingwith, alloccurrences",
		),
		] = "alloccurrences",
		technical_bodies: Annotated[
		str \| None,
		typer.Option(
		help="Comma-separated TB names to filter by (e.g., '3gpp,etsi')",
		),
		] = None,
		output: Annotated[
		OutputFormat,
		typer.Option(
		"--output",
		help="Output format: json, ison, toon, table",
		),
		] = OutputFormat.TABLE,
		) -> None:
		"""Search TEDDI for a term."""
		try:
		# Convert string inputs to enum values
		try:
		si = SearchIn(search_in.lower())
		except ValueError:
		console.print(f"[red]Error: Invalid search-in value '{search_in}'[/red]")
		raise typer.Exit(1) from None

		try:
		sp = SearchPattern(search_pattern.lower())
		except ValueError:
		console.print(f"[red]Error: Invalid search-pattern value '{search_pattern}'[/red]")
		raise typer.Exit(1) from None

		# Parse technical bodies
		tbs: list[TechnicalBody] \| None = None
		if technical_bodies:
		tb_names = [tb.strip() for tb in technical_bodies.split(",")]
		tbs_list: list[TechnicalBody] = []
		for tb_name in tb_names:
		try:
		tb = TechnicalBody(tb_name.lower())
		tbs_list.append(tb)
		except ValueError as exc:
		console.print(f"[red]Error: Unknown technical body '{tb_name}'[/red]")
		raise typer.Exit(1) from exc
		tbs = tbs_list

		# Create search request
		request = SearchRequest(
		term=term,
		search_in=si,
		search_pattern=sp,
		technical_bodies=tbs,
		)

		# Execute search
		async with TeddiClient() as client:
		response = await client.search_terms(request)

		if output == OutputFormat.TABLE:
		_render_table(term, response)
		return

		payload = _build_results_payload(request, response)
		console.print(_serialize_payload(payload, output))

		except typer.Exit:
		raise
		except Exception as e:
		console.print(f"[red]Error during search: {e}[/red]")
		raise typer.Exit(1) from e


		@search_app.command("list-bodies")
		@async_command
		async def list_technical_bodies() -> None:
		"""List all available technical bodies."""
		try:
		async with TeddiClient() as client:
		tbs = await client.get_available_technical_bodies()

		table = Table(title="Available Technical Bodies")
		table.add_column("Code", style="cyan")
		table.add_column("Name", style="white")

		for tb in tbs:
		display_name = {
		"3gpp": "3GPP",
		"3gpp2": "3GPP2",
		"bbcc": "BBCC",
		"ecma": "ECMA",
		"etsi": "ETSI",
		"ietf": "IETF",
		"ieee": "IEEE",
		"iso": "ISO",
		"itu": "ITU",
		"oma": "OMA",
		"zsm": "ZSM",
		}.get(tb.value, tb.value.upper())

		table.add_row(tb.value, display_name)

		console.print(table)

		except Exception as e:
		console.print(f"[red]Error listing technical bodies: {e}[/red]")
		raise typer.Exit(1) from e


		@app.command("server")
		def run_server() -> None:
		"""Start the MCP server on stdio."""

src/teddi-mcp/teddi_mcp/http_client.py

+2 −48

Original line number	Diff line number	Diff line
		@@ -4,58 +4,12 @@ import logging
		from pathlib import Path

		import httpx
		from hishel import AsyncSqliteStorage, SyncSqliteStorage
		from hishel.httpx import AsyncCacheClient, SyncCacheClient
		from hishel import AsyncSqliteStorage
		from hishel.httpx import AsyncCacheClient

		logger = logging.getLogger(__name__)


		def create_cached_teddi_session(
		cache_dir: Path \| None = None,
		cache_ttl: int = 7200,
		refresh_ttl_on_access: bool = True,
		) -> httpx.Client:
		"""Create an httpx.Client with hishel caching for TEDDI requests.

		Args:
		cache_dir: Directory for cache SQLite database. Defaults to `.cache/`.
		cache_ttl: Cache TTL in seconds. Defaults to 2 hours (7200 seconds).
		refresh_ttl_on_access: If True, extends TTL on cache hits. Defaults to True.

		Returns:
		httpx.Client configured with hishel caching.
		"""
		if cache_dir is None:
		cache_dir = Path.cwd() / ".cache"

		cache_dir.mkdir(parents=True, exist_ok=True)
		cache_file = cache_dir / "teddi_http.sqlite3"

		logger.debug(f"HTTP cache: {cache_file}")

		# Create storage backend
		storage = SyncSqliteStorage(
		database_path=str(cache_file),
		default_ttl=cache_ttl,
		refresh_ttl_on_access=refresh_ttl_on_access,
		)

		# Create httpx client with hishel caching
		client = SyncCacheClient(
		storage=storage,
		headers={
		"User-Agent": (
		"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
		"AppleWebKit/537.36 (KHTML, like Gecko) "
		"Chrome/120.0.0.0 Safari/537.36"
		),
		},
		timeout=30.0,
		)

		return client


		async def create_cached_teddi_async_client(
		cache_dir: Path \| None = None,
		cache_ttl: int = 7200,

src/teddi-mcp/teddi_mcp/models.py

+9 −130

Original line number	Diff line number	Diff line
		@@ -4,6 +4,15 @@ from dataclasses import dataclass
		from enum import StrEnum


		class OutputFormat(StrEnum):
		"""Output format for CLI results."""

		JSON = "json"
		ISON = "ison"
		TOON = "toon"
		TABLE = "table"


		class SearchIn(StrEnum):
		"""Search scope: where to search for the term."""

		@@ -25,136 +34,6 @@ class TechnicalBody(StrEnum):
		"""ETSI and standardization body identifiers."""

		ALL = "all"
		THREE_GPP = "3gpp"
		AERO = "aero"
		AFI = "afi"
		ARF = "arf"
		AT = "at"
		ATA = "ata"
		ATM = "atm"
		ATTM = "attm"
		BOARD = "board"
		BRAN = "bran"
		BROADCAS = "broadcas"
		BT = "bt"
		BTC = "btc"
		CABLE = "cable"
		CCM = "ccm"
		CDM = "cdm"
		CIM = "cim"
		CLOUD = "cloud"
		CN = "cn"
		CYBER = "cyber"
		DATA = "data"
		DECT = "dect"
		DTA = "dta"
		E2NA = "e2na"
		E4P = "e4p"
		EASI = "easi"
		ECI = "eci"
		ECMA = "ecma"
		ECMATC32 = "ecmatc32"
		EE = "ee"
		EHEALTH = "ehealth"
		EMTEL = "emtel"
		ENI = "eni"
		ERM = "erm"
		ESI = "esi"
		ETI = "eti"
		ETSI = "etsi"
		F5G = "f5g"
		GA = "ga"
		GRID = "grid"
		HF = "hf"
		ICC = "icc"
		IEEE = "ieee"
		IETF = "ietf"
		IMCC = "imcc"
		INS = "ins"
		INT = "int"
		IP6 = "ip6"
		IPE = "ipe"
		IPRC = "iprc"
		ISAC = "isac"
		ISI = "isi"
		ISM = "ism"
		ISO = "iso"
		ITS = "its"
		ITU = "itu"
		LI = "li"
		LIS = "lis"
		LTN = "ltn"
		M2M = "m2m"
		MAT = "mat"
		MBC = "mbc"
		MCD = "mcd"
		M_COMM = "m-comm"
		MEC = "mec"
		MESA = "mesa"
		MMG = "mmg"
		MOI = "moi"
		MSG = "msg"
		MTA = "mta"
		MTC = "mtc"
		MTS = "mts"
		MWT = "mwt"
		NA = "na"
		NFV = "nfv"
		NGP = "ngp"
		NIN = "nin"
		NTECH = "ntech"
		OCG = "ocg"
		OEU = "oeu"
		OMA = "oma"
		ONEM2M = "onem2m"
		ORI = "ori"
		OSG = "osg"
		OSM = "osm"
		PDL = "pdl"
		PLT = "plt"
		PS = "ps"
		PTS = "pts"
		QKD = "qkd"
		QSC = "qsc"
		RES = "res"
		RIS = "ris"
		RRS = "rrs"
		RT = "rt"
		SAFETY = "safety"
		SAGE = "sage"
		SAI = "sai"
		SCP = "scp"
		SEC = "sec"
		SES = "ses"
		SET = "set"
		SMARTBAN = "smartban"
		SMARTM2M = "smartm2m"
		SMG = "smg"
		SMT = "smt"
		SPAN = "span"
		SPS = "sps"
		STQ = "stq"
		TCCE = "tcce"
		TE = "te"
		TETRA = "tetra"
		THZ = "thz"
		TIPHON = "tiphon"
		TISPAN = "tispan"
		TM = "tm"
		TMN = "tmn"
		TRAC = "trac"
		UMTS = "umts"
		USER = "user"
		ZSM = "zsm"


		class OutputFormat(StrEnum):
		"""Supported CLI output formats."""

		TABLE = "table"
		JSON = "json"
		ISON = "ison"
		TOON = "toon"


		@dataclass

src/teddi-mcp/teddi_mcp/parser.py

+2 −2

Original line number	Diff line number	Diff line
		@@ -3,7 +3,7 @@
		import logging
		from urllib.parse import urljoin

		from bs4 import BeautifulSoup
		from bs4 import BeautifulSoup, Tag

		from teddi_mcp.models import DocumentRef, TermResult

		@@ -119,7 +119,7 @@ def parse_teddi_response(html_content: str) -> list[TermResult]:
		return results


		def _parse_document_table(cell_content) -> list[DocumentRef]:
		def _parse_document_table(cell_content: Tag) -> list[DocumentRef]:
		"""Parse nested table in 'Declared in document(s)' cell with TB grouping.

		Handles TB grouping: if TB column is empty, inherit from previous row.