Spaces:
Build error
Build error
File size: 11,607 Bytes
0fb8136 e0fd571 0fb8136 e0fd571 0fb8136 e0fd571 0fb8136 6736e17 0fb8136 6736e17 0fb8136 6736e17 0fb8136 6736e17 0fb8136 cd353f9 0fb8136 cd353f9 0fb8136 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 | """
Gรฉnรฉrateur METS v1.12 depuis une liste de PageMaster (R02).
Source canonique : liste de PageMaster uniquement โ jamais les rรฉponses brutes.
Les 6 sections obligatoires : metsHdr, dmdSec, amdSec, fileSec,
structMap PHYSICAL, structMap LOGICAL.
fileSec โ 3 fileGrp par manuscrit :
master = URL image originale (master.image["original_url"])
derivative_web = dรฉrivรฉ JPEG (master.image["derivative_web"])
alto = chemin attendu (data/corpora/{slug}/pages/{folio}/alto.xml)
structMap PHYSICAL = sรฉquence des pages triรฉes par master.sequence.
structMap LOGICAL = 1 seul div TYPE="manuscript" (MVP).
"""
# 1. stdlib
import logging
from datetime import datetime, timezone
from pathlib import Path
# 2. third-party
from lxml import etree
# 3. local
from app.schemas.page_master import PageMaster
logger = logging.getLogger(__name__)
# โโ Namespaces METS โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
_METS_NS = "http://www.loc.gov/METS/"
_MODS_NS = "http://www.loc.gov/mods/v3"
_DC_NS = "http://purl.org/dc/elements/1.1/"
_XLINK_NS = "http://www.w3.org/1999/xlink"
_XSI_NS = "http://www.w3.org/2001/XMLSchema-instance"
_SCHEMA_LOC = (
"http://www.loc.gov/METS/ "
"https://www.loc.gov/standards/mets/mets.xsd"
)
_M = f"{{{_METS_NS}}}"
_DC = f"{{{_DC_NS}}}"
_XL = f"{{{_XLINK_NS}}}"
def _el(parent: etree._Element, tag: str, attrib: dict | None = None,
text: str | None = None) -> etree._Element:
el = etree.SubElement(parent, tag, attrib or {})
if text is not None:
el.text = text
return el
def _safe_id(value: str) -> str:
"""Remplace les caractรจres non autorisรฉs dans un ID XML par '_'."""
return value.replace("-", "_").replace(".", "_").replace(" ", "_")
def _alto_path(corpus_slug: str, folio_label: str, base_data_dir: Path) -> str:
"""Retourne le chemin attendu de l'alto.xml pour une page."""
return str(base_data_dir / "corpora" / corpus_slug / "pages" / folio_label / "alto.xml")
def generate_mets(
masters: list[PageMaster],
manuscript_meta: dict,
base_data_dir: Path = Path("data"),
) -> str:
"""Gรฉnรจre le XML METS v1.12 complet pour un manuscrit.
Args:
masters: liste des PageMaster du manuscrit (au moins 1).
manuscript_meta: dict avec les clรฉs :
Obligatoires : manuscript_id (str), label (str), corpus_slug (str)
Optionnelles : language (str), repository (str), shelfmark (str),
date_label (str), institution (str)
base_data_dir: racine du dossier data (pour construire les chemins ALTO).
Returns:
Chaรฎne UTF-8 contenant le XML METS (avec dรฉclaration XML).
Raises:
ValueError: si masters est vide ou si un champ obligatoire est absent.
"""
# โโ Validation des entrรฉes โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
if not masters:
raise ValueError(
"generate_mets : la liste de PageMaster est vide โ "
"un manuscrit doit avoir au moins une page."
)
for key in ("manuscript_id", "label", "corpus_slug"):
if not manuscript_meta.get(key):
raise ValueError(
f"generate_mets : champ obligatoire manquant dans manuscript_meta : ยซ{key}ยป"
)
manuscript_id = manuscript_meta["manuscript_id"]
label = manuscript_meta["label"]
corpus_slug = manuscript_meta["corpus_slug"]
language = manuscript_meta.get("language", "")
repository = manuscript_meta.get("repository", "")
shelfmark = manuscript_meta.get("shelfmark", "")
date_label = manuscript_meta.get("date_label", "")
institution = manuscript_meta.get("institution", "")
# Pages triรฉes par sรฉquence (R02 โ structMap PHYSICAL doit respecter sequence)
pages = sorted(masters, key=lambda m: m.sequence)
now_iso = datetime.now(tz=timezone.utc).isoformat()
# โโ Racine โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
nsmap = {
"mets": _METS_NS,
"dc": _DC_NS,
"xlink": _XLINK_NS,
"xsi": _XSI_NS,
}
root = etree.Element(
f"{_M}mets",
{
"OBJID": manuscript_id,
"TYPE": "Manuscript",
"LABEL": label,
f"{{{_XSI_NS}}}schemaLocation": _SCHEMA_LOC,
},
nsmap=nsmap,
)
# โโ 1. metsHdr โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
hdr = _el(root, f"{_M}metsHdr", {"CREATEDATE": now_iso})
agent = _el(hdr, f"{_M}agent", {"ROLE": "CREATOR", "TYPE": "ORGANIZATION"})
_el(agent, f"{_M}name", text="IIIF Studio")
# โโ 2. dmdSec โ Dublin Core โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
dmd = _el(root, f"{_M}dmdSec", {"ID": "DMD_1"})
wrap = _el(dmd, f"{_M}mdWrap", {"MDTYPE": "DC"})
xml_data = _el(wrap, f"{_M}xmlData")
_el(xml_data, f"{_DC}title", text=label)
_el(xml_data, f"{_DC}identifier", text=manuscript_id)
if language:
_el(xml_data, f"{_DC}language", text=language)
if repository:
_el(xml_data, f"{_DC}source", text=repository)
if shelfmark:
_el(xml_data, f"{_DC}relation", text=shelfmark)
if date_label:
_el(xml_data, f"{_DC}date", text=date_label)
if institution:
_el(xml_data, f"{_DC}publisher", text=institution)
_el(xml_data, f"{_DC}format", text="application/mets+xml")
# โโ 3. amdSec โ techMD global โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
amd = _el(root, f"{_M}amdSec")
tech = _el(amd, f"{_M}techMD", {"ID": "AMD_1"})
amd_wrap = _el(tech, f"{_M}mdWrap", {"MDTYPE": "OTHER", "OTHERMDTYPE": "IIIFStudio"})
amd_data = _el(amd_wrap, f"{_M}xmlData")
# Premier processing trouvรฉ parmi les pages
first_processing = next(
(m.processing for m in pages if m.processing is not None), None
)
amd_root = etree.SubElement(amd_data, "iiifStudioProcessing")
_el(amd_root, "generator", text="IIIF Studio")
_el(amd_root, "pageCount", text=str(len(pages)))
_el(amd_root, "corpusSlug", text=corpus_slug)
if first_processing:
_el(amd_root, "modelId", text=first_processing.model_id)
_el(amd_root, "modelDisplayName", text=first_processing.model_display_name)
_el(amd_root, "processedAt", text=first_processing.processed_at.isoformat())
# โโ 4. fileSec โ 3 fileGrp โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
file_sec = _el(root, f"{_M}fileSec")
grp_master = _el(file_sec, f"{_M}fileGrp", {"USE": "master"})
grp_deriv = _el(file_sec, f"{_M}fileGrp", {"USE": "derivative_web"})
grp_alto = _el(file_sec, f"{_M}fileGrp", {"USE": "alto"})
for page in pages:
sid = _safe_id(page.page_id)
# master image (IIIF service URL ou URL statique)
master_url = page.image.iiif_service_url or page.image.master or ""
if page.image.iiif_service_url:
master_url = f"{page.image.iiif_service_url}/full/max/0/default.jpg"
f_master = _el(grp_master, f"{_M}file", {"ID": f"IMG_MASTER_{sid}", "MIMETYPE": "image/jpeg"})
_el(f_master, f"{_M}FLocat", {
"LOCTYPE": "URL",
f"{_XL}href": master_url,
f"{_XL}type": "simple",
})
# dรฉrivรฉ web (URL IIIF 1500px ou chemin local legacy)
if page.image.iiif_service_url:
deriv_href = f"{page.image.iiif_service_url}/full/!1500,1500/0/default.jpg"
deriv_loctype_attrs = {"LOCTYPE": "URL"}
else:
deriv_href = page.image.derivative_web or ""
deriv_loctype_attrs = {"LOCTYPE": "OTHER", "OTHERLOCTYPE": "filepath"}
f_deriv = _el(grp_deriv, f"{_M}file", {"ID": f"IMG_DERIV_{sid}", "MIMETYPE": "image/jpeg"})
_el(f_deriv, f"{_M}FLocat", {
**deriv_loctype_attrs,
f"{_XL}href": deriv_href,
f"{_XL}type": "simple",
})
# ALTO (rรฉfรฉrence conditionnelle โ warning si le fichier n'existe pas encore)
alto_p = _alto_path(corpus_slug, page.folio_label, base_data_dir)
if not Path(alto_p).exists():
logger.warning(
"Fichier ALTO absent โ la rรฉfรฉrence METS sera cassรฉe tant que l'ALTO n'est pas gรฉnรฉrรฉ",
extra={"alto_path": alto_p, "page_id": page.page_id},
)
f_alto = _el(grp_alto, f"{_M}file", {"ID": f"ALTO_{sid}", "MIMETYPE": "text/xml"})
_el(f_alto, f"{_M}FLocat", {
"LOCTYPE": "OTHER",
"OTHERLOCTYPE": "filepath",
f"{_XL}href": alto_p,
f"{_XL}type": "simple",
})
# โโ 5. structMap PHYSICAL โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
sm_phys = _el(root, f"{_M}structMap", {"TYPE": "PHYSICAL"})
div_seq = _el(sm_phys, f"{_M}div", {"TYPE": "physSequence", "LABEL": label})
for page in pages:
sid = _safe_id(page.page_id)
div_page = _el(div_seq, f"{_M}div", {
"TYPE": "page",
"ORDER": str(page.sequence),
"ORDERLABEL": page.folio_label,
"LABEL": f"Folio {page.folio_label}",
"DMDID": "DMD_1",
})
_el(div_page, f"{_M}fptr", {"FILEID": f"IMG_MASTER_{sid}"})
_el(div_page, f"{_M}fptr", {"FILEID": f"IMG_DERIV_{sid}"})
_el(div_page, f"{_M}fptr", {"FILEID": f"ALTO_{sid}"})
# โโ 6. structMap LOGICAL โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
sm_log = _el(root, f"{_M}structMap", {"TYPE": "LOGICAL"})
_el(sm_log, f"{_M}div", {
"TYPE": "manuscript",
"LABEL": label,
"DMDID": "DMD_1",
})
logger.info(
"METS gรฉnรฉrรฉ",
extra={"manuscript_id": manuscript_id, "pages": len(pages)},
)
return etree.tostring(
root,
xml_declaration=True,
encoding="UTF-8",
pretty_print=True,
).decode("utf-8")
def write_mets(
mets_xml: str,
corpus_slug: str,
base_data_dir: Path = Path("data"),
) -> None:
"""รcrit le XML METS dans data/corpora/{corpus_slug}/mets.xml.
Crรฉe les dossiers parents si nรฉcessaire.
Args:
mets_xml: chaรฎne XML retournรฉe par generate_mets().
corpus_slug: identifiant du corpus (dรฉtermine le rรฉpertoire de sortie).
base_data_dir: racine du dossier data.
"""
output_path = base_data_dir / "corpora" / corpus_slug / "mets.xml"
output_path.parent.mkdir(parents=True, exist_ok=True)
output_path.write_text(mets_xml, encoding="utf-8")
logger.info("mets.xml รฉcrit", extra={"path": str(output_path)})
|