File size: 22,269 Bytes
1ef1de7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
from __future__ import annotations

import csv
import json
import importlib.util
from pathlib import Path

from ocrtech.cli import main
from ocrtech.manifest import ManifestEntry, load_manifest, sha256_file, write_manifest
from ocrtech.source_audit import audit_gorkhapatra_language_pages, audit_gorkhapatra_source, prepare_gorkhapatra_language_page_pack


def test_audit_gorkhapatra_source_parses_local_category_and_epaper_html(tmp_path: Path) -> None:
    category = tmp_path / "category.html"
    category.write_text(
        """
        <html><body>
          <a href="https://gorkhapatraonline.com/news/210290">
            <img alt="समावेशीकरणको दिशामा नयाँ फड्को : गोरखापत्रद्वारा प्रकाशित मगर  भाषा"
                 src="https://gorkhapatraonline.com/storage/media/365132/conversions/6-original-thumb.jpg">
          </a>
          <a href="/news/207983">
            <img alt="समावेशीकरणको दिशामा नयाँ फड्को : गोरखापत्रद्वारा प्रकाशित बान्तावा  भाषा"
                 src="/storage/media/fixture/bantawa.jpg">
          </a>
          <img alt="समावेशीकरणको दिशामा नयाँ फड्को : गोरखापत्रद्वारा प्रकाशित संस्कृत  भाषा"
               src="/storage/media/fixture/sanskrit.jpg">
          <a href="/news/210293">समावेशीकरणको दिशामा नयाँ फड्को : गोरखापत्रद्वारा प्रकाशित संस्कृत  भाषा</a>
        </body></html>
        """,
        encoding="utf-8",
    )
    epaper = tmp_path / "epaper.html"
    epaper.write_text(
        """
        <html><body>
          <a href="https://epaper.gorkhapatraonline.com/pdf?file=/uploads/file/2026/6/gorkhapatra/sample.pdf">
            <img src="/uploads/image/2026/6/gorkhapatra/thumb/sample.jpg">
            <span class="date">२०८३ असार १ सोमवार</span>
          </a>
        </body></html>
        """,
        encoding="utf-8",
    )

    audit = audit_gorkhapatra_source(
        tmp_path / "out",
        category_html_paths=[category],
        epaper_html_paths=[epaper],
    )

    assert audit.article_count == 3
    assert audit.epaper_count == 1
    assert audit.language_counts == {"बान्तावा": 1, "मगर": 1, "संस्कृत": 1}
    assert audit.articles[1].article_url == "https://gorkhapatraonline.com/news/207983"
    assert audit.articles[2].article_url == "https://gorkhapatraonline.com/news/210293"
    assert audit.epapers[0].direct_pdf_url == "https://epaper.gorkhapatraonline.com/uploads/file/2026/6/gorkhapatra/sample.pdf"
    assert (tmp_path / "out" / "gorkhapatra-source-audit.json").exists()
    assert (tmp_path / "out" / "gorkhapatra-source-audit.md").exists()


def test_cli_audit_gorkhapatra_source_downloads_local_article_image(tmp_path: Path, capsys) -> None:
    image = tmp_path / "source.jpg"
    image.write_bytes(b"not really a jpeg")
    category = tmp_path / "category.html"
    category.write_text(
        f"""
        <html><body>
          <a href="https://gorkhapatraonline.com/news/1">
            <img alt="समावेशीकरणको दिशामा नयाँ फड्को : गोरखापत्रद्वारा प्रकाशित लिम्बु भाषा"
                 src="{image.as_uri()}">
          </a>
        </body></html>
        """,
        encoding="utf-8",
    )

    exit_code = main(
        [
            "audit-gorkhapatra-source",
            "--no-default-urls",
            "--category-html",
            str(category),
            "--download-assets",
            "--max-article-images",
            "1",
            "--out",
            str(tmp_path / "audit"),
        ]
    )

    captured = capsys.readouterr()
    payload = json.loads((tmp_path / "audit" / "gorkhapatra-source-audit.json").read_text(encoding="utf-8"))
    assert exit_code == 0
    assert "articles=1 epapers=0 downloaded=1" in captured.out
    assert payload["language_counts"] == {"लिम्बु": 1}
    downloaded = payload["articles"][0]["downloaded_image"]
    assert downloaded["sha256"]
    assert Path(downloaded["path"]).read_bytes() == b"not really a jpeg"


def test_prepare_gorkhapatra_pack_writes_pending_reference_manifest_from_article_images(tmp_path: Path, capsys) -> None:
    image = tmp_path / "source.jpg"
    image.write_bytes(b"article image")
    audit = tmp_path / "source-audit.json"
    audit.write_text(
        json.dumps(
            {
                "articles": [
                    {
                        "article_url": "https://gorkhapatraonline.com/news/limbu",
                        "image_url": "https://gorkhapatraonline.com/storage/limbu.jpg",
                        "title": "समावेशीकरणको दिशामा नयाँ फड्को : गोरखापत्रद्वारा प्रकाशित लिम्बु भाषा",
                        "language": "लिम्बु",
                        "source_page": "fixture",
                        "downloaded_image": {
                            "url": "https://gorkhapatraonline.com/storage/limbu.jpg",
                            "path": str(image),
                            "sha256": "fixture",
                            "size_bytes": image.stat().st_size,
                            "kind": "image",
                            "warnings": [],
                        },
                    }
                ],
                "epapers": [],
            }
        ),
        encoding="utf-8",
    )

    exit_code = main(
        [
            "prepare-gorkhapatra-pack",
            str(audit),
            "--out",
            str(tmp_path / "pack"),
            "--no-epaper-pages",
        ]
    )

    captured = capsys.readouterr()
    entries = load_manifest(tmp_path / "pack" / "manifests" / "gorkhapatra-pack.jsonl")
    reference = json.loads(Path(entries[0].metadata["reference_path"]).read_text(encoding="utf-8"))
    assert exit_code == 0
    assert "samples=1 article_images=1 epaper_pages=0" in captured.out
    assert entries[0].metadata["language"] == "लिम्बु"
    assert entries[0].metadata["reference_status"] == "pending_manual_label"
    assert entries[0].metadata["claim_evidence_eligible"] is False
    assert "language:लिम्बु" in entries[0].metadata["slices"]
    assert Path(entries[0].image_path).read_bytes() == b"article image"
    assert reference["metadata"]["reference_status"] == "pending_manual_label"


def test_prepare_gorkhapatra_pack_renders_epaper_pdf_pages_when_pymupdf_available(tmp_path: Path) -> None:
    if importlib.util.find_spec("fitz") is None:
        return
    import fitz

    pdf = tmp_path / "sample.pdf"
    document = fitz.open()
    page = document.new_page(width=120, height=120)
    page.insert_text((20, 40), "Gorkhapatra")
    document.save(pdf)
    document.close()
    audit = tmp_path / "source-audit.json"
    audit.write_text(
        json.dumps(
            {
                "articles": [],
                "epapers": [
                    {
                        "viewer_url": "https://epaper.gorkhapatraonline.com/pdf?file=/uploads/file/sample.pdf",
                        "direct_pdf_url": "https://epaper.gorkhapatraonline.com/uploads/file/sample.pdf",
                        "source_page": "fixture",
                        "date_label": "२०८३ असार १ सोमवार",
                        "downloaded_pdf": {
                            "url": "https://epaper.gorkhapatraonline.com/uploads/file/sample.pdf",
                            "path": str(pdf),
                            "sha256": "fixture",
                            "size_bytes": pdf.stat().st_size,
                            "kind": "pdf",
                            "warnings": [],
                        },
                    }
                ],
            }
        ),
        encoding="utf-8",
    )

    exit_code = main(
        [
            "prepare-gorkhapatra-pack",
            str(audit),
            "--out",
            str(tmp_path / "pack"),
            "--no-article-images",
            "--max-epaper-pdfs",
            "1",
            "--max-pages-per-pdf",
            "1",
        ]
    )

    entries = load_manifest(tmp_path / "pack" / "manifests" / "gorkhapatra-pack.jsonl")
    assert exit_code == 0
    assert len(entries) == 1
    assert Path(entries[0].image_path).suffix == ".png"
    assert Path(entries[0].image_path).exists()
    assert entries[0].metadata["source_kind"] == "epaper_page"
    assert entries[0].metadata["pdf_page_index"] == 0


def test_audit_gorkhapatra_language_pages_matches_publication_date_to_epaper(tmp_path: Path, capsys) -> None:
    publication = tmp_path / "publication.html"
    publication.write_text(
        """
        <html><body>
          <div class="blog-box-layout1 publication">
            <div class="item-img">
              <a href="https://gorkhapatraonline.com/news/210290">
                <img alt="समावेशीकरणको दिशामा नयाँ फड्को : गोरखापत्रद्वारा प्रकाशित मगर  भाषा"
                     src="https://gorkhapatraonline.com/storage/media/365132/conversions/6-original-thumb.jpg">
              </a>
            </div>
            <div class="item-content">
              <ul class="entry-meta">
                <li><i class="fas fa-user"></i>गोरखापत्र अनलाइन</li>
                <li><i class="fas fa-calendar-alt"></i>१ असार २०८३, सोमबार</li>
              </ul>
              <h3 class="item-title">
                <a href="https://gorkhapatraonline.com/news/210290">समावेशीकरणको दिशामा नयाँ फड्को : गोरखापत्रद्वारा प्रकाशित मगर भाषा</a>
              </h3>
            </div>
          </div>
        </body></html>
        """,
        encoding="utf-8",
    )
    epaper = tmp_path / "epaper.html"
    epaper.write_text(
        """
        <html><body>
          <a href="https://epaper.gorkhapatraonline.com/pdf?file=/uploads/file/2026/6/gorkhapatra/sample.pdf">
            <span class="date">२०८३ असार १ सोमवार</span>
          </a>
        </body></html>
        """,
        encoding="utf-8",
    )

    exit_code = main(
        [
            "audit-gorkhapatra-language-pages",
            "--no-default-urls",
            "--publication-html",
            str(publication),
            "--epaper-html",
            str(epaper),
            "--out",
            str(tmp_path / "out"),
        ]
    )

    captured = capsys.readouterr()
    payload = json.loads((tmp_path / "out" / "gorkhapatra-language-pages.json").read_text(encoding="utf-8"))
    alignment = payload["alignments"][0]
    assert exit_code == 0
    assert "publication_items=1 aligned=1 language_page_hits=0" in captured.out
    assert payload["status_counts"] == {"matched_epaper_not_downloaded": 1}
    assert alignment["publication_item"]["date_key"] == "2083-03-01"
    assert alignment["publication_item"]["language"] == "मगर"
    assert alignment["epaper"]["direct_pdf_url"] == "https://epaper.gorkhapatraonline.com/uploads/file/2026/6/gorkhapatra/sample.pdf"
    assert alignment["claim_evidence_eligible"] is False


def test_audit_gorkhapatra_language_pages_finds_marker_in_downloaded_pdf(tmp_path: Path) -> None:
    if importlib.util.find_spec("fitz") is None:
        return
    import fitz

    pdf = tmp_path / "language-page.pdf"
    document = fitz.open()
    page = document.new_page(width=300, height=300)
    page.insert_text((40, 80), "bhasa pristha")
    page.insert_text((40, 120), "Sample language page body")
    document.save(pdf)
    document.close()
    publication = tmp_path / "publication.html"
    publication.write_text(
        """
        <html><body>
          <a href="https://gorkhapatraonline.com/news/1">
            <img alt="समावेशीकरणको दिशामा नयाँ फड्को : गोरखापत्रद्वारा प्रकाशित लिम्बु भाषा" src="/limbu.jpg">
          </a>
          <ul><li><i class="fas fa-calendar-alt"></i>१ असार २०८३, सोमबार</li></ul>
        </body></html>
        """,
        encoding="utf-8",
    )
    epaper = tmp_path / "epaper.html"
    epaper.write_text(
        f"""
        <html><body>
          <a href="https://epaper.gorkhapatraonline.com/pdf?file={pdf.as_uri()}">
            <span class="date">२०८३ असार १ सोमवार</span>
          </a>
        </body></html>
        """,
        encoding="utf-8",
    )

    audit = audit_gorkhapatra_language_pages(
        tmp_path / "out",
        publication_html_paths=[publication],
        epaper_html_paths=[epaper],
        download_pdfs=True,
        render_pages=True,
    )

    assert audit.language_page_hit_count == 1
    assert audit.alignments[0].alignment_status == "language_page_found"
    assert audit.alignments[0].page_hits[0].page_index == 0
    assert audit.alignments[0].page_hits[0].rendered_page_path is not None
    assert Path(audit.alignments[0].page_hits[0].rendered_page_path).exists()


def test_prepare_gorkhapatra_language_page_pack_writes_pending_manifest(tmp_path: Path, capsys) -> None:
    rendered = tmp_path / "page.png"
    rendered.write_bytes(b"rendered page")
    audit = tmp_path / "language-pages.json"
    audit.write_text(
        json.dumps(
            {
                "alignments": [
                    {
                        "publication_item": {
                            "article_url": "https://gorkhapatraonline.com/news/210290",
                            "image_url": "https://gorkhapatraonline.com/storage/media/365132/6.jpg",
                            "title": "समावेशीकरणको दिशामा नयाँ फड्को : गोरखापत्रद्वारा प्रकाशित मगर भाषा",
                            "language": "मगर",
                            "date_label": "१ असार २०८३, सोमबार",
                            "date_key": "2083-03-01",
                            "source_page": "fixture",
                        },
                        "epaper": {
                            "viewer_url": "https://epaper.gorkhapatraonline.com/pdf?file=/uploads/file/sample.pdf",
                            "direct_pdf_url": "https://epaper.gorkhapatraonline.com/uploads/file/sample.pdf",
                            "source_page": "fixture",
                            "date_label": "२०८३ असार १ सोमवार",
                            "thumbnail_url": None,
                            "downloaded_pdf": None,
                        },
                        "pdf_path": str(tmp_path / "sample.pdf"),
                        "pdf_sha256": "pdfhash",
                        "page_hits": [
                            {
                                "page_index": 5,
                                "marker": "efiff k[i7",
                                "text_chars": 120,
                                "text_preview": "efiff k[i7",
                                "rendered_page_path": str(rendered),
                            }
                        ],
                        "alignment_status": "language_page_found",
                        "claim_evidence_eligible": False,
                        "warnings": [],
                    }
                ]
            }
        ),
        encoding="utf-8",
    )

    exit_code = main(
        [
            "prepare-gorkhapatra-language-page-pack",
            str(audit),
            "--out",
            str(tmp_path / "pack"),
        ]
    )

    captured = capsys.readouterr()
    entries = load_manifest(tmp_path / "pack" / "manifests" / "gorkhapatra-language-page-pack.jsonl")
    reference = json.loads(Path(entries[0].metadata["reference_path"]).read_text(encoding="utf-8"))
    assert exit_code == 0
    assert "samples=1 copied_pages=1 warnings=0" in captured.out
    assert len(entries) == 1
    assert Path(entries[0].image_path).read_bytes() == b"rendered page"
    assert entries[0].metadata["candidate_language"] == "मगर"
    assert entries[0].metadata["pdf_page_number"] == 6
    assert entries[0].metadata["page_disambiguation_status"] == "candidate_requires_manual_review"
    assert entries[0].metadata["reference_status"] == "pending_manual_label"
    assert entries[0].metadata["claim_evidence_eligible"] is False
    assert "language_page_candidate" in entries[0].metadata["slices"]
    assert reference["metadata"]["source_kind"] == "gorkhapatra_language_page_candidate"


def test_prepare_gorkhapatra_language_page_pack_records_missing_rendered_pages(tmp_path: Path) -> None:
    audit = tmp_path / "language-pages.json"
    audit.write_text(
        json.dumps(
            {
                "alignments": [
                    {
                        "publication_item": {"language": "मगर", "date_key": "2083-03-01"},
                        "page_hits": [{"page_index": 5, "marker": "efiff k[i7"}],
                    }
                ]
            }
        ),
        encoding="utf-8",
    )

    summary = prepare_gorkhapatra_language_page_pack(audit, tmp_path / "pack")

    assert summary.sample_count == 0
    assert summary.warnings == ["alignment 1 page hit 1 has no rendered_page_path"]


def test_prepare_gorkhapatra_language_page_review_writes_manual_review_artifacts(tmp_path: Path, capsys) -> None:
    image_one = tmp_path / "page-one.png"
    image_two = tmp_path / "page-two.png"
    image_one.write_bytes(b"candidate one")
    image_two.write_bytes(b"candidate two")
    ref_one = tmp_path / "page-one.ref.json"
    ref_two = tmp_path / "page-two.ref.json"
    ref_one.write_text("{}", encoding="utf-8")
    ref_two.write_text("{}", encoding="utf-8")
    manifest = tmp_path / "manifest.jsonl"
    write_manifest(
        [
            ManifestEntry(
                sample_id="gorkhapatra-language-page-0001-01",
                dataset="fixture",
                split="eval",
                image_path=str(image_one),
                text="",
                sha256=sha256_file(image_one),
                metadata={
                    "source_kind": "language_page_candidate",
                    "candidate_language": "संस्कृत",
                    "date_label": "१ असार २०८३, सोमबार",
                    "date_key": "2083-03-01",
                    "pdf_page_index": 5,
                    "pdf_page_number": 6,
                    "reference_path": str(ref_one),
                    "article_url": "https://gorkhapatraonline.com/news/1",
                    "source_image_url": "https://gorkhapatraonline.com/storage/1.jpg",
                    "source_url": "https://epaper.gorkhapatraonline.com/uploads/file/sample.pdf",
                    "pdf_path": str(tmp_path / "sample.pdf"),
                    "pdf_sha256": "pdfhash",
                    "language_page_marker": "efiff k[i7",
                    "alignment_status": "language_page_found",
                    "page_disambiguation_status": "candidate_requires_manual_review",
                    "reference_status": "pending_manual_label",
                    "claim_evidence_eligible": False,
                },
            ),
            ManifestEntry(
                sample_id="gorkhapatra-language-page-0002-01",
                dataset="fixture",
                split="eval",
                image_path=str(image_two),
                text="",
                sha256=sha256_file(image_two),
                metadata={
                    "source_kind": "language_page_candidate",
                    "candidate_language": "मगर",
                    "date_key": "2083-03-01",
                    "pdf_page_index": 5,
                    "pdf_page_number": 6,
                    "reference_path": str(ref_two),
                    "source_url": "https://epaper.gorkhapatraonline.com/uploads/file/sample.pdf",
                    "language_page_marker": "efiff k[i7",
                    "alignment_status": "language_page_found",
                    "page_disambiguation_status": "candidate_requires_manual_review",
                    "reference_status": "pending_manual_label",
                    "claim_evidence_eligible": False,
                },
            ),
        ],
        manifest,
    )

    exit_code = main(
        [
            "prepare-gorkhapatra-language-page-review",
            str(manifest),
            "--out",
            str(tmp_path / "review"),
        ]
    )

    captured = capsys.readouterr()
    payload = json.loads((tmp_path / "review" / "gorkhapatra-language-page-review.json").read_text(encoding="utf-8"))
    with (tmp_path / "review" / "gorkhapatra-language-page-review.csv").open("r", encoding="utf-8", newline="") as handle:
        csv_rows = list(csv.DictReader(handle))
    markdown = (tmp_path / "review" / "gorkhapatra-language-page-review.md").read_text(encoding="utf-8")
    assert exit_code == 0
    assert "samples=2 pending_review=2 claim_eligible=0 warnings=0" in captured.out
    assert payload["summary"]["sample_count"] == 2
    assert payload["summary"]["page_candidate_counts"] == {"2083-03-01:page-6": 2}
    assert payload["rows"][0]["review_decision"] == ""
    assert payload["rows"][0]["claim_evidence_eligible"] is False
    assert csv_rows[1]["candidate_language"] == "मगर"
    assert csv_rows[1]["reviewer"] == ""
    assert "Rows remain non-claim-ready" in markdown