flowdeck/app/services/importers/notion.py

"""FlowDeck — Notion export importer (v5.6.0, Phase 1, amélioration v5.4.0).

Imports a Notion "Export as Markdown & CSV" ``.zip``: complete page hierarchy,
databases (``.csv``) turned into FlowDeck collections, and image attachments.
"""
from __future__ import annotations

import csv
import io
import re
import zipfile
from urllib.parse import unquote

from app.services.importers._common import split_frontmatter
from app.services.importers.base import (
    ImportAttachment,
    Importer,
    ImportPage,
    ImportResult,
    decode_text,
    register_importer,
)
from app.services.importers.tabular import rows_to_collection

_HASH_RE = re.compile(r"\s+[0-9a-f]{32}$")
_MD_LINK_RE = re.compile(r"\]\(([^)]+)\.md\)")


def _clean_name(name: str) -> str:
    base = unquote(name.replace("\\", "/").rsplit("/", 1)[-1])
    base = re.sub(r"\.(md|csv|markdown)$", "", base, flags=re.IGNORECASE)
    return _HASH_RE.sub("", base).strip() or "Untitled"


def _strip_hash_link(match: re.Match) -> str:
    target = unquote(match.group(1)).strip()
    return f"]({_HASH_RE.sub('', target).strip() or target})"


@register_importer
class NotionImporter(Importer):
    source_id = "notion"
    label = "Notion (export .zip)"
    description = "Export Notion Markdown & CSV : hiérarchie, databases → collections, images."
    extensions = (".zip",)
    order = 20

    def detect(self, filename: str, data: bytes) -> bool:
        if not filename.lower().endswith(".zip"):
            return False
        try:
            zf = zipfile.ZipFile(io.BytesIO(data))
        except (zipfile.BadZipFile, OSError):
            return False
        names = [n for n in zf.namelist() if not n.endswith("/")]
        md = [n for n in names if n.lower().endswith(".md")]
        csvs = [n for n in names if n.lower().endswith(".csv")]
        if not md:
            return False
        if csvs:
            return True
        return any(_HASH_RE.search(unquote(n.rsplit("/", 1)[-1])) for n in md)

    def parse(self, filename: str, data: bytes) -> ImportResult:
        result = ImportResult(source=self.source_id)
        try:
            zf = zipfile.ZipFile(io.BytesIO(data))
        except (zipfile.BadZipFile, OSError) as exc:
            result.warn(f"Archive invalide : {exc}")
            return result.finalize()

        names = [n for n in zf.namelist() if not n.endswith("/")]
        md_names = [n for n in names if n.lower().endswith(".md")]
        csv_names = [n for n in names if n.lower().endswith(".csv")]

        pages_by_title: dict[str, ImportPage] = {}
        for name in sorted(md_names, key=lambda n: (n.count("/"), n.lower())):
            try:
                text = decode_text(zf.read(name))
            except Exception as exc:  # noqa: BLE001
                result.warn(f"Lecture impossible : {name} ({exc})")
                continue
            meta, body = split_frontmatter(text)
            title = _clean_name(name)
            body = _MD_LINK_RE.sub(_strip_hash_link, body)
            first_line = body.lstrip().splitlines()[0] if body.strip() else ""
            if first_line.strip().startswith("# ") and first_line.strip()[2:].strip() == title:
                body = "\n".join(body.lstrip().splitlines()[1:]).lstrip("\n")
            parts = unquote(name).replace("\\", "/").split("/")
            page = ImportPage(
                title=title,
                markdown=body,
                source_path=name,
                parent_path="/".join(parts[:-1]),
                properties={k: v for k, v in meta.items() if k != "title"},
                external_id=name,
            )
            pages_by_title.setdefault(title, page)
            result.pages.append(page)

        for name in sorted(csv_names, key=lambda n: (n.count("/"), n.lower())):
            try:
                text = decode_text(zf.read(name))
            except Exception as exc:  # noqa: BLE001
                result.warn(f"Lecture impossible : {name} ({exc})")
                continue
            reader = csv.DictReader(io.StringIO(text))
            headers = [h for h in (reader.fieldnames or []) if h is not None]
            rows = [dict(r) for r in reader]
            title = _clean_name(name)
            spec_page = rows_to_collection(title, headers, rows)
            parts = unquote(name).replace("\\", "/").split("/")
            existing = pages_by_title.get(title)
            if existing is not None:
                existing.collection = spec_page.collection
                existing.source_path = existing.source_path or name
            else:
                spec_page.parent_path = "/".join(parts[:-1])
                spec_page.source_path = name
                spec_page.external_id = name
                result.pages.append(spec_page)

        for name in names:
            low = name.lower()
            if low.endswith((".md", ".csv")):
                continue
            try:
                result.attachments.append(ImportAttachment(
                    source_path=name,
                    filename=unquote(name).replace("\\", "/").rsplit("/", 1)[-1],
                    data=zf.read(name),
                ))
            except Exception:  # noqa: BLE001
                continue
        return result.finalize()