Initial SQL-only 1C adapter baseline

This commit is contained in:
2026-07-22 03:03:47 +03:00
commit e2503b77e7
545 changed files with 184711 additions and 0 deletions
+191
View File
@@ -0,0 +1,191 @@
from __future__ import annotations
import argparse
import json
from pathlib import Path
from typing import Any
from urllib import request
def rpc(adapter_url: str, method: str, payload: dict[str, Any]) -> dict[str, Any]:
body = json.dumps({"method": method, "payload": payload}, ensure_ascii=False).encode("utf-8")
req = request.Request(
f"{adapter_url.rstrip('/')}/rpc",
data=body,
headers={"Content-Type": "application/json; charset=utf-8"},
method="POST",
)
with request.urlopen(req, timeout=240) as resp:
return json.loads(resp.read().decode("utf-8", errors="replace"))
def latest_configcas_rows(adapter_url: str, base_id: str, limit: int) -> list[dict[str, Any]]:
result = rpc(
adapter_url,
"query.run",
{
"base_id": base_id,
"diagnostic": True,
"query": (
f"SELECT TOP {int(limit)} FileName, DATALENGTH(BinaryData) AS Bytes, PartNo, Creation, Modified "
"FROM ConfigCAS ORDER BY Modified DESC"
),
"timeout_seconds": 120,
},
)
return result.get("rows") or []
def read_structure(adapter_url: str, base_id: str, file_name: str, max_cells: int) -> dict[str, Any]:
result = rpc(
adapter_url,
"templates.map",
{
"base_id": base_id,
"table": "ConfigCAS",
"file_name": file_name,
"view": "summary",
"sections": "cells,styles,named_areas,named_ranges,diagnostics",
"max_cells": max_cells,
"max_areas": 200,
"timeout_seconds": 120,
},
)
templates = result.get("templates") or []
if not templates:
return {}
item = templates[0] or {}
structure = item.get("structure") or {}
route = item.get("route") or {}
return {"structure": structure, "route": route}
def summarize_candidate(row: dict[str, Any], structure_bundle: dict[str, Any]) -> dict[str, Any]:
structure = structure_bundle.get("structure") or {}
route = structure_bundle.get("route") or {}
counts = structure.get("counts") or {}
named_areas = [item.get("name") for item in (structure.get("named_areas") or []) if isinstance(item, dict) and item.get("name")]
named_ranges = [item.get("name") for item in (structure.get("named_range_candidates") or []) if isinstance(item, dict) and item.get("name")]
cells = structure.get("cells") or []
styles = structure.get("cell_style_candidates") or []
sample_texts: list[str] = []
for item in cells:
if not isinstance(item, dict):
continue
text = str(item.get("text") or "")
if text and text not in sample_texts:
sample_texts.append(text)
if len(sample_texts) >= 12:
break
sample_style_texts: list[str] = []
for item in styles:
if not isinstance(item, dict):
continue
text = str(item.get("text") or "")
if text and text not in sample_style_texts:
sample_style_texts.append(text)
if len(sample_style_texts) >= 12:
break
return {
"file_name": row.get("FileName"),
"bytes": row.get("Bytes"),
"modified": row.get("Modified"),
"format": structure.get("format"),
"dimensions": structure.get("dimensions"),
"counts": counts,
"capabilities": structure.get("capabilities") or {},
"named_areas": named_areas,
"named_ranges": named_ranges,
"sample_texts": sample_texts,
"sample_style_texts": sample_style_texts,
"route": route,
}
def is_interesting(summary: dict[str, Any]) -> bool:
if str(summary.get("format") or "") == "MOXCEL":
return True
counts = summary.get("counts") or {}
return any(
int(counts.get(key) or 0) > 0
for key in ("cells", "cell_style_candidates", "named_areas", "named_range_candidates")
)
def render_markdown(payload: dict[str, Any]) -> str:
lines: list[str] = []
lines.append("# 1C template payload inventory")
lines.append("")
lines.append(f"- Base: `{payload.get('base_id')}`")
lines.append(f"- Scanned rows: `{payload.get('scan_limit')}`")
lines.append(f"- Interesting payloads: `{len(payload.get('items') or [])}`")
lines.append("")
lines.append("| File | Bytes | Modified | Format | Named ranges | Sample texts |")
lines.append("| --- | --- | --- | --- | --- | --- |")
for item in payload.get("items") or []:
named_ranges = ", ".join(item.get("named_ranges") or [])
sample_texts = ", ".join(item.get("sample_texts") or [])
lines.append(
f"| `{item.get('file_name')}` | `{item.get('bytes')}` | `{item.get('modified')}` | "
f"`{item.get('format')}` | `{named_ranges}` | `{sample_texts}` |"
)
return "\n".join(lines) + "\n"
def main() -> int:
parser = argparse.ArgumentParser(description="Inventory recent 1C template payload candidates from ConfigCAS.")
parser.add_argument("--adapter-url", default="http://docker-gpu.cin.su:8011")
parser.add_argument("--base-id", default="upo_test")
parser.add_argument("--scan-limit", type=int, default=200)
parser.add_argument("--max-cells", type=int, default=200)
parser.add_argument(
"--output-json",
default=str(Path("Z:/codex/LLM/reports/1c-template-baselines/upo_test_template_payload_inventory.json")),
)
parser.add_argument(
"--output-markdown",
default=str(Path("Z:/codex/LLM/reports/1c-template-baselines/upo_test_template_payload_inventory.md")),
)
args = parser.parse_args()
rows = latest_configcas_rows(args.adapter_url, args.base_id, args.scan_limit)
items: list[dict[str, Any]] = []
for row in rows:
file_name = str(row.get("FileName") or "")
byte_count = int(row.get("Bytes") or 0)
if not file_name or byte_count <= 0 or byte_count > 20000:
continue
bundle = read_structure(args.adapter_url, args.base_id, file_name, args.max_cells)
summary = summarize_candidate(row, bundle)
if is_interesting(summary):
items.append(summary)
payload = {
"schema": "codex_1c_template_payload_inventory.v1",
"adapter_url": args.adapter_url,
"base_id": args.base_id,
"scan_limit": args.scan_limit,
"items": items,
"counts": {"items": len(items)},
}
json_path = Path(args.output_json)
md_path = Path(args.output_markdown)
json_path.write_text(json.dumps(payload, ensure_ascii=False, indent=2), encoding="utf-8")
md_path.write_text(render_markdown(payload), encoding="utf-8")
print(
json.dumps(
{
"status": "ok",
"json": str(json_path),
"markdown": str(md_path),
"items": len(items),
},
ensure_ascii=False,
indent=2,
)
)
return 0
if __name__ == "__main__":
raise SystemExit(main())