utility-app/scripts/build-legal-profile-from-old-app.py

import json
import re
import subprocess
from pathlib import Path

OLD_APP = Path("/mnt/storage/sftp/mcelwain/repository/word-doc-generator")
DRAFT_PROFILE = Path("diagnostics/legacy_word_doc_generator_profile_draft.json")
OUT_PROFILE = Path("tools/doc_generator/content/document_types/legal_profile.json")
TEMPLATES_OUT = Path("tools/doc_generator/content/templates/legacy")

OLD_PUBLIC = OLD_APP / "public"


def run_node_list_extractor():
    js = f"""
import {{ pathToFileURL }} from 'url';

const files = [
  'casePlaintiffInfo.js',
  'opposingCounselInfo.js',
  'judgeInfo.js',
  'caseFilingAttorneyInfo.js',
  'filingAttorneyInfo.js',
  'debtCollectorInfo.js'
];

const base = {json.dumps(str(OLD_PUBLIC))};
const result = {{}};

for (const file of files) {{
  try {{
    const mod = await import(pathToFileURL(`${{base}}/${{file}}`).href);
    for (const [exportName, value] of Object.entries(mod)) {{
      if (value && typeof value === 'object' && !Array.isArray(value)) {{
        result[exportName] = Object.keys(value).sort();
      }}
    }}
  }} catch (err) {{
    // Some optional info files may not exist.
  }}
}}

console.log(JSON.stringify(result));
"""
    try:
        completed = subprocess.run(
            ["node", "--input-type=module", "-e", js],
            check=True,
            capture_output=True,
            text=True,
        )
        return json.loads(completed.stdout)
    except Exception:
        return {}


def nice_label(name):
    label = re.sub(r"([a-z])([A-Z])", r"\1 \2", name)
    label = label.replace("_", " ").replace("-", " ")
    label = re.sub(r"\bSsn\b", "SSN", label.title())
    label = label.replace("Dob", "DOB")
    return label


def apply_legal_field_metadata(field):
    name = field["name"]
    lower = name.lower()

    # Normalize generated labels.
    field["label"] = nice_label(name)

    # Autocomplete fields.
    if name == "casePlaintiff":
        field["type"] = "autocomplete"
        field["list"] = "plaintiffs"
    elif name == "caseOpposingCounsel":
        field["type"] = "autocomplete"
        field["list"] = "opposingCounsel"
    elif name == "caseDivisionJudge":
        field["type"] = "autocomplete"
        field["list"] = "judges"
    elif name == "caseFilingAttorney":
        field["type"] = "autocomplete"
        field["list"] = "filingAttorneys"
    elif re.fullmatch(r"debtCollector\d+Name", name):
        field["type"] = "autocomplete"
        field["list"] = "debtCollectors"
    elif lower.endswith("state") or name in {"caseState", "homeState", "client2homeState"}:
        field["type"] = "autocomplete"
        field["list"] = "states"
    elif name == "caseDesignation":
        field["type"] = "autocomplete"
        field["list"] = "caseDesignations"

    # Long text fields.
    if name in {"notes", "caseAppearanceInfo", "paymentOptions", "paymentOptions1", "paymentOptions2", "paymentOptions3", "paymentOptions4", "paymentOptions5"}:
        field["type"] = "textarea"

    return field


def walk_sections(sections):
    for section in sections:
        section["collapsible"] = section.get("heading") not in {
            "Client Information",
            "Case Information",
        }
        section["defaultOpen"] = section.get("heading") in {
            "Client Information",
            "Case Information",
        }

        section["fields"] = [
            apply_legal_field_metadata(field)
            for field in section.get("fields", [])
        ]

        for subsection in section.get("subsections", []):
            walk_sections([subsection])


def discover_templates():
    templates = []

    for path in sorted(TEMPLATES_OUT.rglob("*.docx")):
        rel = path.relative_to(Path("tools/doc_generator/content/templates")).as_posix()
        template_id = re.sub(r"[^a-zA-Z0-9]+", "_", path.stem).strip("_").lower()

        label = path.relative_to(TEMPLATES_OUT).as_posix()
        label = label.replace(".docx", "")
        label = label.replace("/", " / ")
        label = label.replace("_", " ")

        templates.append({
            "id": template_id,
            "label": label,
            "template": rel,
            "outputFilename": f"{template_id}_{{caseNumber}}_{{timestamp_YYYY-MM-DD_HH-mm-ss}}.docx"
        })

    return templates


def main():
    if not DRAFT_PROFILE.exists():
        raise SystemExit(f"Missing {DRAFT_PROFILE}. Run review-old-word-doc-generator.py first.")

    draft = json.loads(DRAFT_PROFILE.read_text(encoding="utf-8"))

    lists_raw = run_node_list_extractor()

    lists = {
        "plaintiffs": lists_raw.get("casePlaintiffInfo", []),
        "opposingCounsel": lists_raw.get("caseOpposingCounselInfo", []) or lists_raw.get("opposingCounselInfo", []),
        "judges": lists_raw.get("judgeInfo", []),
        "filingAttorneys": lists_raw.get("caseFilingAttorneyInfo", []) or lists_raw.get("filingAttorneyInfo", []),
        "debtCollectors": lists_raw.get("debtCollectorInfo", []),
        "states": ["MO", "KS"],
        "caseDesignations": [
            "Associate Circuit",
            "Circuit",
            "Limited Actions",
            "Small Claims"
        ]
    }

    sections = draft["sections"]
    walk_sections(sections)

    templates = discover_templates()

    profile = {
        "id": "legal_profile",
        "name": "Legal Profile",
        "description": "Consumer debt defense legal profile generated from the legacy word-doc-generator app.",
        "template": templates[0]["template"] if templates else "legacy/Canned-Emails.docx",
        "outputFilename": "legal_{caseNumber}_{timestamp_YYYY-MM-DD_HH-mm-ss}.docx",
        "lists": lists,
        "templates": templates,
        "sections": sections
    }

    OUT_PROFILE.parent.mkdir(parents=True, exist_ok=True)
    OUT_PROFILE.write_text(json.dumps(profile, indent=2), encoding="utf-8")

    print(f"Wrote {OUT_PROFILE}")
    print(f"Lists: {', '.join(f'{k}={len(v)}' for k, v in lists.items())}")
    print(f"Templates: {len(templates)}")


if __name__ == "__main__":
    main()