"""The workflow's upload step, split into the run context file and the files it lists (ADR 0018). `parse_assessment_files` hands every step one string: the files in upload order, joined by FILE_SEPARATOR, with no file names in the text. The run context file is always first (kab_run_workflow.py uploads it first), and its `uploads:` list names the files after it, in order. This file is identical in the planner, inventory, reconciliation and report agents (a test in each compares it with the planner's). It knows no column of any file: a table is a header line and one line per row. No runtime imports. """ from __future__ import annotations import re from typing import Any, Dict, List, Optional, Tuple import yaml FILE_SEPARATOR = "\n\n---\n\n" # data_file_processing.FILE_SEPARATOR SHEET_HEADER = re.compile(r"^=== Sheet: (.*) ===$") # data_file_processing.SHEET_HEADER, one per XLSX sheet EMPTY_FRAME = "Empty DataFrame" # pandas' rendering of a sheet or CSV with no rows PARSE_ERRORS = ("Excel parsing error:", "CSV parsing error:", "PDF parsing error:", "Error parsing ", "[Error parsing file:") # the platform returns a failed parse as text, not an error ROW_INDEX = r"^\s*(\d+)\s" # pandas puts the row index first on each row line class UploadUnreadable(ValueError): """A listed upload is missing, or the platform couldn't parse it.""" def _yaml(text: str) -> Dict[str, Any]: try: data = yaml.safe_load(text) except yaml.YAMLError: return {} return data if isinstance(data, dict) else {} def _entry(item: Any) -> Dict[str, Any]: if isinstance(item, dict): return {"name": str(item.get("name") or ""), "source": str(item.get("source") or "").lower() or None, "format": item.get("format")} return {"name": str(item), "source": None, "format": None} def split(parsed_content: Optional[str]) -> Dict[str, Any]: """{"context": the run context as a dict ({} if it isn't YAML), "context_text": its text, "uploads": [{"name", "source", "format", "text"}] for each entry in its `uploads:`, in order}. The text is split at most once per listed upload, so a separator inside the last upload never cuts it short. A listed upload with no part of its own has text None. """ text = parsed_content or "" first = text.split(FILE_SEPARATOR, 1)[0] doc = _yaml(first) listed = doc.get("uploads") if isinstance(doc.get("uploads"), list) else [] parts = text.split(FILE_SEPARATOR, len(listed)) if listed else [text] uploads = [] for index, item in enumerate(listed, start=1): entry = _entry(item) entry["text"] = parts[index] if index < len(parts) else None uploads.append(entry) return {"context": doc, "context_text": parts[0], "uploads": uploads} def context_section(parsed_content: Optional[str]) -> Dict[str, Any]: """The run context's `context:` section, or {}.""" section = split(parsed_content)["context"].get("context") return section if isinstance(section, dict) else {} def uploads_from(parsed_content: Optional[str], source: str) -> List[Dict[str, Any]]: """The listed uploads whose `source:` is this one (e.g. cmdb).""" return [u for u in split(parsed_content)["uploads"] if u["source"] == source] def _rows(lines: List[str]) -> List[Tuple[int, str]]: found = [re.match(ROW_INDEX, line) for line in lines] numbers = [int(m.group(1)) for m in found if m] if len(numbers) == len(lines) and len(set(numbers)) == len(numbers): return list(zip(numbers, lines)) return list(enumerate(lines)) # not a pandas table (a raw CSV, say): number rows by position def _table(sheet: Optional[str], lines: List[str]) -> Dict[str, Any]: lines = [line.rstrip() for line in lines if line.strip()] if not lines or lines[0].strip().startswith(EMPTY_FRAME): return {"sheet": sheet, "header": lines[0] if lines else "", "rows": []} return {"sheet": sheet, "header": lines[0], "rows": _rows(lines[1:])} def tables(upload: Dict[str, Any]) -> List[Dict[str, Any]]: """[{"sheet": name or None, "header": the header line, "rows": [(row number, line)]}] for one upload. Raises UploadUnreadable for a missing upload or one the platform failed to parse.""" text = upload.get("text") if text is None or not text.strip(): raise UploadUnreadable(f"{upload.get('name')}: listed in the run context's uploads but not uploaded") if text.strip().startswith(PARSE_ERRORS): raise UploadUnreadable(f"{upload.get('name')}: the platform could not parse it: {text.strip()[:200]}") sheets: List[Tuple[Optional[str], List[str]]] = [] current: Tuple[Optional[str], List[str]] = (None, []) for line in text.split("\n"): header = SHEET_HEADER.match(line.strip()) if header: if current[0] is not None or any(x.strip() for x in current[1]): sheets.append(current) current = (header.group(1), []) else: current[1].append(line) sheets.append(current) return [_table(sheet, lines) for sheet, lines in sheets]