fixed the tests

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
This commit is contained in:
Peter Staar 2024-11-07 05:15:13 +01:00
parent b154d4f2d7
commit 5c82ff9890
5 changed files with 17 additions and 4427 deletions

View File

@ -114,14 +114,18 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
_log.info(f" -> error treating child: {exc}") _log.info(f" -> error treating child: {exc}")
raise exc raise exc
else:
_log.debug(f"ignoring element of type {type(element)}")
"""
elif isinstance(element, Tag): elif isinstance(element, Tag):
try: try:
self.analyse_element(element, 0, doc) self.analyse_element(element, 0, doc)
except Exception as exc: except Exception as exc:
_log.info(f" -> error treating elem: {exc}") _log.info(f" -> error treating elem: {exc}")
raise exc raise exc
else: """
_log.debug(f"ignoring element of type {type(element)}")
except Exception as exc: except Exception as exc:
_log.debug(f"error walking element: {type(element)}") _log.debug(f"error walking element: {type(element)}")

View File

@ -77,6 +77,7 @@ def export_documents(
export_md: bool, export_md: bool,
export_txt: bool, export_txt: bool,
export_doctags: bool, export_doctags: bool,
export_itxt: bool,
): ):
success_count = 0 success_count = 0
@ -115,6 +116,12 @@ def export_documents(
_log.info(f"writing Doc Tags output to {fname}") _log.info(f"writing Doc Tags output to {fname}")
fp.write(conv_res.document.export_to_document_tokens()) fp.write(conv_res.document.export_to_document_tokens())
# Export Indented Text format:
if export_itxt:
fname = output_dir / f"{doc_filename}.itxt"
with fname.open("w") as fp:
_log.info(f"writing Doc Tags output to {fname}")
fp.write(conv_res.document._export_to_indented_text())
else: else:
_log.warning(f"Document {conv_res.input.file} failed to convert.") _log.warning(f"Document {conv_res.input.file} failed to convert.")
failure_count += 1 failure_count += 1
@ -200,6 +207,7 @@ def convert(
export_md = OutputFormat.MARKDOWN in to_formats export_md = OutputFormat.MARKDOWN in to_formats
export_txt = OutputFormat.TEXT in to_formats export_txt = OutputFormat.TEXT in to_formats
export_doctags = OutputFormat.DOCTAGS in to_formats export_doctags = OutputFormat.DOCTAGS in to_formats
export_itxt = OutputFormat.INDENTED_TEXT in to_formats
match ocr_engine: match ocr_engine:
case OcrEngine.EASYOCR: case OcrEngine.EASYOCR:
@ -243,6 +251,7 @@ def convert(
export_md=export_md, export_md=export_md,
export_txt=export_txt, export_txt=export_txt,
export_doctags=export_doctags, export_doctags=export_doctags,
export_itxt=export_itxt,
) )
end_time = time.time() - start_time end_time = time.time() - start_time

View File

@ -39,6 +39,7 @@ class OutputFormat(str, Enum):
JSON = "json" JSON = "json"
TEXT = "text" TEXT = "text"
DOCTAGS = "doctags" DOCTAGS = "doctags"
INDENTED_TEXT = "itxt"
FormatToExtensions: Dict[InputFormat, List[str]] = { FormatToExtensions: Dict[InputFormat, List[str]] = {

View File

@ -388,319 +388,3 @@ item-0 at level 0: unspecified: group _root_
item-374 at level 4: list_item: Mobile view item-374 at level 4: list_item: Mobile view
item-375 at level 3: list: group list item-375 at level 3: list: group list
item-376 at level 3: list: group list item-376 at level 3: list: group list
item-377 at level 4: list: group list
item-378 at level 5: list: group list
item-379 at level 6: list: group list
item-380 at level 7: list: group list
item-381 at level 8: list: group list
item-382 at level 9: list: group list
item-383 at level 10: list: group list
item-384 at level 11: list: group list
item-385 at level 12: list: group list
item-386 at level 13: list: group list
item-387 at level 14: list: group list
item-388 at level 15: list: group list
item-389 at level 16: list: group list
item-390 at level 17: list: group list
item-391 at level 18: list: group list
item-392 at level 19: list: group list
item-393 at level 20: list: group list
item-394 at level 21: list: group list
item-395 at level 22: list: group list
item-396 at level 23: list: group list
item-397 at level 24: list: group list
item-398 at level 25: list: group list
item-399 at level 26: list: group list
item-400 at level 27: list: group list
item-401 at level 28: list: group list
item-402 at level 29: list: group list
item-403 at level 30: list: group list
item-404 at level 31: list: group list
item-405 at level 32: list: group list
item-406 at level 33: list: group list
item-407 at level 34: list: group list
item-408 at level 35: list: group list
item-409 at level 36: list: group list
item-410 at level 37: list: group list
item-411 at level 38: list: group list
item-412 at level 39: list: group list
item-413 at level 40: list: group list
item-414 at level 41: list: group list
item-415 at level 42: list: group list
item-416 at level 43: list: group list
item-417 at level 44: list: group list
item-418 at level 45: list: group list
item-419 at level 46: list: group list
item-420 at level 47: list: group list
item-421 at level 48: list: group list
item-422 at level 49: list: group list
item-423 at level 50: list: group list
item-424 at level 51: list: group list
item-425 at level 52: list: group list
item-426 at level 53: list: group list
item-427 at level 54: list: group list
item-428 at level 55: list: group list
item-429 at level 56: list: group list
item-430 at level 57: list: group list
item-431 at level 58: list: group list
item-432 at level 59: list: group list
item-433 at level 60: list: group list
item-434 at level 61: list: group list
item-435 at level 62: list: group list
item-436 at level 63: list: group list
item-437 at level 64: list: group list
item-438 at level 65: list: group list
item-439 at level 66: list: group list
item-440 at level 67: list: group list
item-441 at level 68: list: group list
item-442 at level 69: list: group list
item-443 at level 70: list: group list
item-444 at level 71: list: group list
item-445 at level 72: list: group list
item-446 at level 73: list: group list
item-447 at level 74: list: group list
item-448 at level 75: list: group list
item-449 at level 76: list: group list
item-450 at level 77: list: group list
item-451 at level 78: list: group list
item-452 at level 79: list: group list
item-453 at level 80: list: group list
item-454 at level 81: list: group list
item-455 at level 82: list: group list
item-456 at level 83: list: group list
item-457 at level 84: list: group list
item-458 at level 85: list: group list
item-459 at level 86: list: group list
item-460 at level 87: list: group list
item-461 at level 88: list: group list
item-462 at level 89: list: group list
item-463 at level 90: list: group list
item-464 at level 91: list: group list
item-465 at level 92: list: group list
item-466 at level 93: list: group list
item-467 at level 94: list: group list
item-468 at level 95: list: group list
item-469 at level 96: list: group list
item-470 at level 97: list: group list
item-471 at level 98: list: group list
item-472 at level 99: list: group list
item-473 at level 100: list: group list
item-474 at level 101: list: group list
item-475 at level 102: list: group list
item-476 at level 103: list: group list
item-477 at level 104: list: group list
item-478 at level 105: list: group list
item-479 at level 106: list: group list
item-480 at level 107: list: group list
item-481 at level 108: list: group list
item-482 at level 109: list: group list
item-483 at level 110: list: group list
item-484 at level 111: list: group list
item-485 at level 112: list: group list
item-486 at level 113: list: group list
item-487 at level 114: list: group list
item-488 at level 115: list: group list
item-489 at level 116: list: group list
item-490 at level 117: list: group list
item-491 at level 118: list: group list
item-492 at level 119: list: group list
item-493 at level 120: list: group list
item-494 at level 121: list: group list
item-495 at level 122: list: group list
item-496 at level 123: list: group list
item-497 at level 124: list: group list
item-498 at level 125: list: group list
item-499 at level 126: list: group list
item-500 at level 127: list: group list
item-501 at level 128: list: group list
item-502 at level 129: list: group list
item-503 at level 130: list: group list
item-504 at level 131: list: group list
item-505 at level 132: list: group list
item-506 at level 133: list: group list
item-507 at level 134: list: group list
item-508 at level 135: list: group list
item-509 at level 136: list: group list
item-510 at level 137: list: group list
item-511 at level 138: list: group list
item-512 at level 139: list: group list
item-513 at level 140: list: group list
item-514 at level 141: list: group list
item-515 at level 142: list: group list
item-516 at level 143: list: group list
item-517 at level 144: list: group list
item-518 at level 145: list: group list
item-519 at level 146: list: group list
item-520 at level 147: list: group list
item-521 at level 148: list: group list
item-522 at level 149: list: group list
item-523 at level 150: list: group list
item-524 at level 151: list: group list
item-525 at level 152: list: group list
item-526 at level 153: list: group list
item-527 at level 154: list: group list
item-528 at level 155: list: group list
item-529 at level 156: list: group list
item-530 at level 157: list: group list
item-531 at level 158: list: group list
item-532 at level 159: list: group list
item-533 at level 160: list: group list
item-534 at level 161: list: group list
item-535 at level 162: list: group list
item-536 at level 163: list: group list
item-537 at level 164: list: group list
item-538 at level 165: list: group list
item-539 at level 166: list: group list
item-540 at level 167: list: group list
item-541 at level 168: list: group list
item-542 at level 169: list: group list
item-543 at level 170: list: group list
item-544 at level 171: list: group list
item-545 at level 172: list: group list
item-546 at level 173: list: group list
item-547 at level 174: list: group list
item-548 at level 175: list: group list
item-549 at level 176: list: group list
item-550 at level 177: list: group list
item-551 at level 178: list: group list
item-552 at level 179: list: group list
item-553 at level 180: list: group list
item-554 at level 181: list: group list
item-555 at level 182: list: group list
item-556 at level 183: list: group list
item-557 at level 184: list: group list
item-558 at level 185: list: group list
item-559 at level 186: list: group list
item-560 at level 187: list: group list
item-561 at level 188: list: group list
item-562 at level 189: list: group list
item-563 at level 190: list: group list
item-564 at level 191: list: group list
item-565 at level 192: list: group list
item-566 at level 193: list: group list
item-567 at level 194: list: group list
item-568 at level 195: list: group list
item-569 at level 196: list: group list
item-570 at level 197: list: group list
item-571 at level 198: list: group list
item-572 at level 199: list: group list
item-573 at level 200: list: group list
item-574 at level 201: list: group list
item-575 at level 202: list: group list
item-576 at level 203: list: group list
item-577 at level 204: list: group list
item-578 at level 205: list: group list
item-579 at level 206: list: group list
item-580 at level 207: list: group list
item-581 at level 208: list: group list
item-582 at level 209: list: group list
item-583 at level 210: list: group list
item-584 at level 211: list: group list
item-585 at level 212: list: group list
item-586 at level 213: list: group list
item-587 at level 214: list: group list
item-588 at level 215: list: group list
item-589 at level 216: list: group list
item-590 at level 217: list: group list
item-591 at level 218: list: group list
item-592 at level 219: list: group list
item-593 at level 220: list: group list
item-594 at level 221: list: group list
item-595 at level 222: list: group list
item-596 at level 223: list: group list
item-597 at level 224: list: group list
item-598 at level 225: list: group list
item-599 at level 226: list: group list
item-600 at level 227: list: group list
item-601 at level 228: list: group list
item-602 at level 229: list: group list
item-603 at level 230: list: group list
item-604 at level 231: list: group list
item-605 at level 232: list: group list
item-606 at level 233: list: group list
item-607 at level 234: list: group list
item-608 at level 235: list: group list
item-609 at level 236: list: group list
item-610 at level 237: list: group list
item-611 at level 238: list: group list
item-612 at level 239: list: group list
item-613 at level 240: list: group list
item-614 at level 241: list: group list
item-615 at level 242: list: group list
item-616 at level 243: list: group list
item-617 at level 244: list: group list
item-618 at level 245: list: group list
item-619 at level 246: list: group list
item-620 at level 247: list: group list
item-621 at level 248: list: group list
item-622 at level 249: list: group list
item-623 at level 250: list: group list
item-624 at level 251: list: group list
item-625 at level 252: list: group list
item-626 at level 253: list: group list
item-627 at level 254: list: group list
item-628 at level 255: list: group list
item-629 at level 256: list: group list
item-630 at level 257: list: group list
item-631 at level 258: list: group list
item-632 at level 259: list: group list
item-633 at level 260: list: group list
item-634 at level 261: list: group list
item-635 at level 262: list: group list
item-636 at level 263: list: group list
item-637 at level 264: list: group list
item-638 at level 265: list: group list
item-639 at level 266: list: group list
item-640 at level 267: list: group list
item-641 at level 268: list: group list
item-642 at level 269: list: group list
item-643 at level 270: list: group list
item-644 at level 271: list: group list
item-645 at level 272: list: group list
item-646 at level 273: list: group list
item-647 at level 274: list: group list
item-648 at level 275: list: group list
item-649 at level 276: list: group list
item-650 at level 277: list: group list
item-651 at level 278: list: group list
item-652 at level 279: list: group list
item-653 at level 280: list: group list
item-654 at level 281: list: group list
item-655 at level 282: list: group list
item-656 at level 283: list: group list
item-657 at level 284: list: group list
item-658 at level 285: list: group list
item-659 at level 286: list: group list
item-660 at level 287: list: group list
item-661 at level 288: list: group list
item-662 at level 289: list: group list
item-663 at level 290: list: group list
item-664 at level 291: list: group list
item-665 at level 292: list: group list
item-666 at level 293: list: group list
item-667 at level 294: list: group list
item-668 at level 295: list: group list
item-669 at level 296: list: group list
item-670 at level 297: list: group list
item-671 at level 298: list: group list
item-672 at level 299: list: group list
item-673 at level 300: list: group list
item-674 at level 301: list: group list
item-675 at level 302: list: group list
item-676 at level 303: list: group list
item-677 at level 304: list: group list
item-678 at level 305: list: group list
item-679 at level 306: list: group list
item-680 at level 307: list: group list
item-681 at level 308: list: group list
item-682 at level 309: list: group list
item-683 at level 310: list: group list
item-684 at level 311: list: group list
item-685 at level 312: list: group list
item-686 at level 313: list: group list
item-687 at level 314: list: group list
item-688 at level 315: list: group list
item-689 at level 316: list: group list
item-690 at level 317: list: group list
item-691 at level 318: list: group list
item-692 at level 319: list: group list

File diff suppressed because it is too large Load Diff