Extend character manifest to external sources
This commit is contained in:
732642856
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,46 @@
|
||||
# External High-Relevance Inventory Manifest
|
||||
|
||||
- status: pass
|
||||
- scope: external
|
||||
- generated_at: 2026-07-02T09:12:09.488794+00:00
|
||||
- total_files: 883
|
||||
- unhashed_files: 0
|
||||
- unclassified_files: 0
|
||||
- unknown_extraction_status: 0
|
||||
- Heavy OCR: disabled
|
||||
- Whole-machine scan: disabled
|
||||
|
||||
## Root Summary
|
||||
|
||||
| Root | Files | Bytes |
|
||||
| --- | ---: | ---: |
|
||||
| `~/.workbuddy` | 767 | 40507359 |
|
||||
| `~/Desktop` | 5 | 1616896 |
|
||||
| `~/Documents/ObsidianVault` | 11 | 45553 |
|
||||
| `~/Downloads` | 15 | 5701907 |
|
||||
| `~/WorkBuddy` | 36 | 665806 |
|
||||
| `~/engines-repo` | 6 | 53358668 |
|
||||
| `~/文件仓库` | 43 | 161766552 |
|
||||
|
||||
## Extraction Status Counts
|
||||
|
||||
- `binary_indexed`: 83
|
||||
- `document_text_extraction_queued`: 11
|
||||
- `image_ocr_queued`: 50
|
||||
- `pdf_text_extraction_queued`: 2
|
||||
- `text_decode_lossy`: 2
|
||||
- `text_indexed`: 735
|
||||
|
||||
## Classification Counts
|
||||
|
||||
- `external_archive_or_binary`: 23
|
||||
- `external_book_or_document`: 46
|
||||
- `external_engine_fragment`: 10
|
||||
- `external_historical_report`: 37
|
||||
- `external_skill_fragment`: 767
|
||||
|
||||
## Boundary
|
||||
|
||||
External scan is high-relevance only. It records hashes and extraction states without copying private source text into repo truth.
|
||||
|
||||
This manifest proves indexing, hashing, and extraction-state classification. It does not by itself promote any source into the runtime truth chain.
|
||||
@@ -0,0 +1,758 @@
|
||||
{
|
||||
"scope": "extraction-queue",
|
||||
"status": "pass",
|
||||
"generated_at": "2026-07-02T09:12:17.049464+00:00",
|
||||
"mode": {
|
||||
"heavy_ocr": false,
|
||||
"whole_machine_scan": false,
|
||||
"external_high_relevance_scan": true,
|
||||
"semantic_promotion": false,
|
||||
"boundary": "Queue only. It identifies PDF/image/document extraction work without performing OCR or promoting extracted text."
|
||||
},
|
||||
"summary": {
|
||||
"queued_files": 66,
|
||||
"unhashed_files": 0,
|
||||
"source_counts": {
|
||||
"external": 63,
|
||||
"project": 3
|
||||
}
|
||||
},
|
||||
"queue_counts": {
|
||||
"document_text_extraction_queued": 11,
|
||||
"image_ocr_queued": 53,
|
||||
"pdf_text_extraction_queued": 2
|
||||
},
|
||||
"queue": [
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Desktop/一楠印度占星 Level 3 综合解盘.docx",
|
||||
"suffix": ".docx",
|
||||
"byte_count": 19165,
|
||||
"sha256": "cee1d2837d7e1d396fe3b6ba06012e16e0dad3d2d68554e5116d25789170b64b",
|
||||
"extraction_status": "document_text_extraction_queued",
|
||||
"classification": "external_historical_report",
|
||||
"priority": "priority_2",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Desktop/印度占星修正版研究结论v3-高压基建后的反转兑现模型.docx",
|
||||
"suffix": ".docx",
|
||||
"byte_count": 21966,
|
||||
"sha256": "b8d1b8c9bae94d7b1102db321543ef34cf4d4b5d7b822c3365e059903be40fb4",
|
||||
"extraction_status": "document_text_extraction_queued",
|
||||
"classification": "external_historical_report",
|
||||
"priority": "priority_2",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/jyotish_training.agent.final.docx",
|
||||
"suffix": ".docx",
|
||||
"byte_count": 186879,
|
||||
"sha256": "a0d83aa8a70f9966cbe79945c4416906e1382c9093998c23d73bd395b02f23fe",
|
||||
"extraction_status": "document_text_extraction_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/WorkBuddy/2026-06-09-20-03-34/jyotish-fragments/training/jyotish_training.agent.final.docx",
|
||||
"suffix": ".docx",
|
||||
"byte_count": 186879,
|
||||
"sha256": "a0d83aa8a70f9966cbe79945c4416906e1382c9093998c23d73bd395b02f23fe",
|
||||
"extraction_status": "document_text_extraction_queued",
|
||||
"classification": "external_historical_report",
|
||||
"priority": "priority_2",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/1印度占星.docx",
|
||||
"suffix": ".docx",
|
||||
"byte_count": 6142110,
|
||||
"sha256": "210a09d764f8fe17ded6c908d5073648908892a99ae853f983e6f516ccc0164d",
|
||||
"extraction_status": "document_text_extraction_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/2印度占星.docx",
|
||||
"suffix": ".docx",
|
||||
"byte_count": 3031411,
|
||||
"sha256": "16979422e7621475243e2739fda00767d1a9dc367f7f10153fe36d8af6e15c6d",
|
||||
"extraction_status": "document_text_extraction_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/3印度占星.docx",
|
||||
"suffix": ".docx",
|
||||
"byte_count": 2149772,
|
||||
"sha256": "59ee274246547f4afb581ec26f5a4aad03ba2095309d66c40a60a51d1244df92",
|
||||
"extraction_status": "document_text_extraction_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/4印度占星.docx",
|
||||
"suffix": ".docx",
|
||||
"byte_count": 5572637,
|
||||
"sha256": "e789430dc1df6ab7054a5b28f0665da325e7c5eb2e6daac39f1f17ac29ba7629",
|
||||
"extraction_status": "document_text_extraction_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/Tajika占星术是印度占星术体系之一.docx",
|
||||
"suffix": ".docx",
|
||||
"byte_count": 1338151,
|
||||
"sha256": "254624594c26fc80ad5bfa9e9a880ac0cd81c9388b19721d5767dfa5c55e953c",
|
||||
"extraction_status": "document_text_extraction_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星Jaimini系统的Darakaraka的理解和说明如何解释.docx",
|
||||
"suffix": ".docx",
|
||||
"byte_count": 44926,
|
||||
"sha256": "f2db03d1c0392e2cdad66da9a731117c0ddf290cad7712b9c3de0d8234a17a29",
|
||||
"extraction_status": "document_text_extraction_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/高地位配偶与婚后命运积极转变的占星规则与组合.docx",
|
||||
"suffix": ".docx",
|
||||
"byte_count": 1120887,
|
||||
"sha256": "9cdd6996670ad46063c9582957c6d98269e069f96801ff340ce0c84de325d412",
|
||||
"extraction_status": "document_text_extraction_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/.workbuddy/skills/jyotish-vedic-astrology/assets/jyotish-logo.png",
|
||||
"suffix": ".png",
|
||||
"byte_count": 1496430,
|
||||
"sha256": "4cb571aa402da3a730a73b6594ec88adf90f2d807018e23f96fd1bee426c23ed",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_skill_fragment",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_candidate"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/.workbuddy/skills/jyotish-vedic-astrology/references/open_source_sources/VedicAstro/VedicAstroLogo.png",
|
||||
"suffix": ".png",
|
||||
"byte_count": 151345,
|
||||
"sha256": "e64022e2dde10d7ce378a69f8b7f035b084d56517f37eb8f6ecc4bd47fe0fe2a",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_skill_fragment",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_candidate"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/.workbuddy/skills/jyotish-vedic-astrology/references/open_source_sources/vedic-astro-skills/assets/alipay.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 164821,
|
||||
"sha256": "f7d4dcf08239c738d5cd45d531401bdef92e4c1b7ea93965b7a7f51ab76dc8fc",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_skill_fragment",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_candidate"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/.workbuddy/skills/jyotish-vedic-astrology/references/open_source_sources/vedic-astro-skills/assets/wechat.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 71804,
|
||||
"sha256": "e94c027499059e7fb2170474fb03e3be875b4251dfbea5fc7f39b370d6242a62",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_skill_fragment",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_candidate"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Desktop/电脑相册/重复图片移动前备份清单_2026-05-20/file_backups/WorkBuddy/yinduzhanxing/assets/jyotish-logo.png",
|
||||
"suffix": ".png",
|
||||
"byte_count": 1496430,
|
||||
"sha256": "4cb571aa402da3a730a73b6594ec88adf90f2d807018e23f96fd1bee426c23ed",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_historical_report",
|
||||
"priority": "priority_2",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星11页/IMG_3004.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 335978,
|
||||
"sha256": "3e87432635d0b7d6181a5d251191ab397352bfc0908bedef4d07b135aa351012",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星11页/IMG_3005.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 365592,
|
||||
"sha256": "3743a89d6611dd8a3a344db2e9ca6877b6f1f610b48bd3cbb9486eb8a81f4195",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星11页/IMG_3006.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 387356,
|
||||
"sha256": "03689b8775950267002cbbf9b96bf5038217c692c311188429ee99903beea285",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星11页/IMG_3007.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 457489,
|
||||
"sha256": "d959e3b1625ec6d7d0a3129f8fd856f18b06de2d4b874bbc3322e1c9818b5aa3",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星11页/IMG_3008.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 447919,
|
||||
"sha256": "8999a66852d45b5e89b53823bff4aecb5b3fca935495572ee3422c1a067d2507",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星11页/IMG_3009.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 436786,
|
||||
"sha256": "e4a1eaa1730a22d96e4032bf405e0ed556395a0d9a27a2c5ec7265b8a3c3fdf8",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星11页/IMG_3010.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 352127,
|
||||
"sha256": "b6478c3db82ad67534fae2bcd52e29da9bb1ffa573271097e8449cfbf1be5537",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星11页/IMG_3011.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 347111,
|
||||
"sha256": "0d786f1284ff916f37055c77101559955e83eecba24b290eb80ab808e7a90ce4",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星11页/IMG_3012.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 282794,
|
||||
"sha256": "319b2ab6948d82e04eaf957caf5310c85f9c42db66f2c39f8e27bcca7528487a",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星11页/IMG_3013.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 296069,
|
||||
"sha256": "2253eebdc5a3f7b26400cffd3b0de32b33b29896783406b85a537957059c3115",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星11页/IMG_3014.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 288473,
|
||||
"sha256": "5d7e8abcd4cdb922d0da0fa987fd4264b57339230586b38570a360f2b1f6f1cd",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/占星印度1/IMG_3223.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 6709612,
|
||||
"sha256": "8a2f44bc4c57b8d352371101a662305b88d4f834d385c22a6f0b308c66119890",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/占星印度1/IMG_3224.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 4388817,
|
||||
"sha256": "30b7f2ea6bcc962ccb3064f3656e7d298a5469e084d1fdf21322bc5ea3b21d90",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/占星印度1/IMG_3225.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 3539980,
|
||||
"sha256": "4edcfa12004b48047dbff7f5512914aedd40768b37dc75ad45c467c05802ab25",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/占星印度1/IMG_3226.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 3118339,
|
||||
"sha256": "820f1c29b11e09ed51681be292adf15919ca3d5157b23fb29d098023f4423c52",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/占星印度1/IMG_3227.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 6945195,
|
||||
"sha256": "c6643554be26edc62274f8b4e0acd1cf305aaeff8c1720cb5b731e0842fada46",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/占星印度1/IMG_3228.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 2188130,
|
||||
"sha256": "d118ce2ed91a3a3b3551833f20cca6604011d22ff921976d50e5cd21d08db3e7",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/占星印度1/IMG_3229.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 1390060,
|
||||
"sha256": "630e6f8f91bfda5fcb3871c30758dec2db32108b89ec511d25aebea7313f0cfe",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/占星印度1/IMG_3230.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 2723452,
|
||||
"sha256": "be3a1ddb38f42961273827537ce8a8c73dd2c5ad5e1effd90c49bcf623b196c2",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/占星印度1/IMG_3231.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 3460758,
|
||||
"sha256": "279b99af4faa614eb21ef8d2a2bc67bf87a4cce112ba04627bca67f2f343297b",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/占星印度1/IMG_3232.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 3256088,
|
||||
"sha256": "a46fb026076a3314ef9f263a7234659c7d2b75068aba20271d07d0f7a3b674b1",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3233.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 5620475,
|
||||
"sha256": "c3ed9e4d29163d9baa0f8b95669cfcbb52f20727ce23f105c5fc8c688cbd5fb6",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3234.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 4739555,
|
||||
"sha256": "1833b90c725ae183f3acf28bc7738858f7750e4dff67bd7157a70fb168c3301a",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3235.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 5869585,
|
||||
"sha256": "13a85b875309b89a47cfe13e52998cf85b1e5da09cc0905ac967877bb0f00091",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3236.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 8733982,
|
||||
"sha256": "6cd213236d66c235c8fe54722411375144e988029ef959a9e051f186399bbbc6",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3237.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 5434137,
|
||||
"sha256": "8a3eda7d1936530abb1ed5c93040b316bd013f02155d2b20eb9626bd84e7480e",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3238.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 5918325,
|
||||
"sha256": "c29063134357d4c7cb081d14c35c5558a47685913eff21be4a229703edd7256b",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3239.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 5110208,
|
||||
"sha256": "6633e0045710c1f6defda6624ec7c8ccf1c22dcb3bc34bf41bba7f48153a3255",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3240.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 4155054,
|
||||
"sha256": "5003bc196b649a9ee6f2cf1583ca55f13cc695030571184c5bf6db429775a5a6",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3241.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 1262218,
|
||||
"sha256": "4ffe9f3aadd4485ba99382a84d54abb02ae2520d8b0f57147fa7438408ce39d4",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3242.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 1867271,
|
||||
"sha256": "a15fadbbd4a250a30bac8e27915210b67fa6dc2ceb482b6a3792a0acba87bd77",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3243.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 6305912,
|
||||
"sha256": "64bd2a3a548a2c94372c1e3312e9f87bd291a276e73a3918fcc903e41f0fea9f",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3244.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 7177473,
|
||||
"sha256": "e7a486925218295da284ca6ca167ae92f2a37285e26ea5161094f531cd12ebd4",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3245.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 6429277,
|
||||
"sha256": "c5fd2b815ca6d295b8de5402084a9a7cdd3f9d2f08e53c50abd45b1352eb8b06",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3246.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 92516,
|
||||
"sha256": "355ae43a243fcdea344500b1b3f53a47683050cd73b01428fa9490844d04e222",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3247.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 7406196,
|
||||
"sha256": "0bc4a95e8d9ad41e6df47cd80a7cf84b2df24cb5400b9de56d63d3be66818e7f",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3248.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 3862462,
|
||||
"sha256": "a3b3f89232cece9d3475cd48a3fff7878a62233743927fa2492b2bb646dfefa3",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3249.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 7780975,
|
||||
"sha256": "8ae9bd3960a150e88feb78813d245c73aa2e6473ff16182a61632241f9f50014",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/印度占星查悦/IMG_3250.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 7389728,
|
||||
"sha256": "6c895f9ddd16c2a1edf785858203cbec1a86c1abb3c6b24e03d24e74d1ea175d",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/受孕/IMG_3216.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 1441554,
|
||||
"sha256": "3cdbdd47967592f2581b820b9df49aecd7117b377c45c71571b440cce3f5dddd",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/受孕/IMG_3218.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 1968582,
|
||||
"sha256": "58d9de5cd5399e74e007d7d50f093dc50d7d0688df484a26646787a07a0c7e92",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/受孕/IMG_3219.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 2710815,
|
||||
"sha256": "47bedfc7e2fdc225305afc31cc4ab74bd0021bd65e61b9d85e1b0909aa5950b6",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/受孕/IMG_3220.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 741635,
|
||||
"sha256": "771256b16a47d9db785abbeab01b11388900e7e98d45220ff0defb52f24e7b1b",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/受孕/IMG_3221.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 1275215,
|
||||
"sha256": "b219ca2e664ddff55ef95681aeaf5362c3a1589b2bef562129e39e8960e0202e",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/文件仓库/印度占星文章/受孕/IMG_3222.JPG",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 1340781,
|
||||
"sha256": "a7601e255c4d398d2480dc71fb99916aa67c56f978a722943970806f805bde26",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "project",
|
||||
"path": "references/open_source_sources/VedicAstro/VedicAstroLogo.png",
|
||||
"suffix": ".png",
|
||||
"byte_count": 151345,
|
||||
"sha256": "e64022e2dde10d7ce378a69f8b7f035b084d56517f37eb8f6ecc4bd47fe0fe2a",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "open_source_reference",
|
||||
"priority": "priority_2",
|
||||
"promotion_status": "reference_layer_candidate"
|
||||
},
|
||||
{
|
||||
"source_scope": "project",
|
||||
"path": "references/open_source_sources/vedic-astro-skills/assets/alipay.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 164821,
|
||||
"sha256": "f7d4dcf08239c738d5cd45d531401bdef92e4c1b7ea93965b7a7f51ab76dc8fc",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "open_source_reference",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "reference_layer_candidate"
|
||||
},
|
||||
{
|
||||
"source_scope": "project",
|
||||
"path": "references/open_source_sources/vedic-astro-skills/assets/wechat.jpg",
|
||||
"suffix": ".jpg",
|
||||
"byte_count": 71804,
|
||||
"sha256": "e94c027499059e7fb2170474fb03e3be875b4251dfbea5fc7f39b370d6242a62",
|
||||
"extraction_status": "image_ocr_queued",
|
||||
"classification": "open_source_reference",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "reference_layer_candidate"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星.pdf",
|
||||
"suffix": ".pdf",
|
||||
"byte_count": 135905,
|
||||
"sha256": "121507cf1d0d66711bc30c18f589f36f2d3cce797ecb13cdf4427625e6ec8894",
|
||||
"extraction_status": "pdf_text_extraction_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
},
|
||||
{
|
||||
"source_scope": "external",
|
||||
"path": "/Users/wuyongnaren/Downloads/印度占星1.pdf",
|
||||
"suffix": ".pdf",
|
||||
"byte_count": 132486,
|
||||
"sha256": "92c9288c5d0011a869c545e3459f037ff09cd20f7508543bc0eb11b03079d930",
|
||||
"extraction_status": "pdf_text_extraction_queued",
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only"
|
||||
}
|
||||
],
|
||||
"artifacts": {
|
||||
"json_report": "docs/research/character_level_extraction_queue_latest.json",
|
||||
"markdown_report": "docs/research/character_level_extraction_queue_latest.md"
|
||||
},
|
||||
"title": "Extraction Queue Manifest"
|
||||
}
|
||||
@@ -0,0 +1,26 @@
|
||||
# Extraction Queue Manifest
|
||||
|
||||
- status: pass
|
||||
- scope: extraction-queue
|
||||
- generated_at: 2026-07-02T09:12:17.049464+00:00
|
||||
- queued_files: 66
|
||||
- unhashed_files: 0
|
||||
- Heavy OCR: disabled
|
||||
- Whole-machine scan: disabled
|
||||
|
||||
## Queue Counts
|
||||
|
||||
- `document_text_extraction_queued`: 11
|
||||
- `image_ocr_queued`: 53
|
||||
- `pdf_text_extraction_queued`: 2
|
||||
|
||||
## Source Counts
|
||||
|
||||
- `external`: 63
|
||||
- `project`: 3
|
||||
|
||||
## Boundary
|
||||
|
||||
Queue only. It identifies PDF/image/document extraction work without performing OCR or promoting extracted text.
|
||||
|
||||
Queued files are indexed by path, size, hash, and extraction status only. Private source text is not copied into this report.
|
||||
@@ -1,10 +1,11 @@
|
||||
{
|
||||
"scope": "project",
|
||||
"status": "pass",
|
||||
"generated_at": "2026-07-02T08:50:52.465261+00:00",
|
||||
"generated_at": "2026-07-02T09:11:51.839696+00:00",
|
||||
"mode": {
|
||||
"heavy_ocr": false,
|
||||
"whole_machine_scan": false,
|
||||
"external_high_relevance_scan": false,
|
||||
"semantic_promotion": false,
|
||||
"boundary": "Fast manifest only: hashes and cheap text stats now; heavy OCR and whole-machine scan are queued."
|
||||
},
|
||||
@@ -16,7 +17,7 @@
|
||||
"AGENTS.md"
|
||||
],
|
||||
"summary": {
|
||||
"total_files": 1069,
|
||||
"total_files": 1073,
|
||||
"unhashed_files": 0,
|
||||
"unclassified_files": 0,
|
||||
"unknown_extraction_status": 0,
|
||||
@@ -27,12 +28,12 @@
|
||||
"quarantined_draft": 93,
|
||||
"real_case_calibration": 5,
|
||||
"reference_candidate": 180,
|
||||
"research_governance": 439
|
||||
"research_governance": 443
|
||||
},
|
||||
"extraction_status_counts": {
|
||||
"binary_indexed": 34,
|
||||
"image_ocr_queued": 3,
|
||||
"text_indexed": 1032
|
||||
"text_indexed": 1036
|
||||
}
|
||||
},
|
||||
"root_summary": {
|
||||
@@ -45,8 +46,8 @@
|
||||
"bytes": 43187
|
||||
},
|
||||
"docs/research": {
|
||||
"files": 532,
|
||||
"bytes": 2198779
|
||||
"files": 536,
|
||||
"bytes": 2901473
|
||||
},
|
||||
"references": {
|
||||
"files": 236,
|
||||
@@ -5168,14 +5169,70 @@
|
||||
"promotion_status": "governance_or_history",
|
||||
"reason": "Research history or governance record; index separately from rule truth."
|
||||
},
|
||||
"docs/research/character_level_external_manifest_latest.json": {
|
||||
"path": "docs/research/character_level_external_manifest_latest.json",
|
||||
"suffix": ".json",
|
||||
"byte_count": 666472,
|
||||
"sha256": "244465beREDACTED_TIMEe81a2c8b3abac4f41e28bd55ce9f42f3f203d6574c52617dcfd9",
|
||||
"extraction_status": "text_indexed",
|
||||
"character_count": 661666,
|
||||
"line_count": 12446,
|
||||
"decode_replacement_count": 0,
|
||||
"classification": "research_governance",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "governance_or_history",
|
||||
"reason": "Research history or governance record; index separately from rule truth."
|
||||
},
|
||||
"docs/research/character_level_external_manifest_latest.md": {
|
||||
"path": "docs/research/character_level_external_manifest_latest.md",
|
||||
"suffix": ".md",
|
||||
"byte_count": 1280,
|
||||
"sha256": "71cc5b027ea056c23ce1d5d1cda8921eeade065a8cb003910ea44d2a1165e642",
|
||||
"extraction_status": "text_indexed",
|
||||
"character_count": 1272,
|
||||
"line_count": 47,
|
||||
"decode_replacement_count": 0,
|
||||
"classification": "research_governance",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "governance_or_history",
|
||||
"reason": "Research history or governance record; index separately from rule truth."
|
||||
},
|
||||
"docs/research/character_level_extraction_queue_latest.json": {
|
||||
"path": "docs/research/character_level_extraction_queue_latest.json",
|
||||
"suffix": ".json",
|
||||
"byte_count": 31649,
|
||||
"sha256": "cbfc03eee31d16cc3c796728cf34504c6eaa0722c5e42dd2f7d2ec1da966c5ef",
|
||||
"extraction_status": "text_indexed",
|
||||
"character_count": 30151,
|
||||
"line_count": 758,
|
||||
"decode_replacement_count": 0,
|
||||
"classification": "research_governance",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "governance_or_history",
|
||||
"reason": "Research history or governance record; index separately from rule truth."
|
||||
},
|
||||
"docs/research/character_level_extraction_queue_latest.md": {
|
||||
"path": "docs/research/character_level_extraction_queue_latest.md",
|
||||
"suffix": ".md",
|
||||
"byte_count": 633,
|
||||
"sha256": "6a45bb22f9f44d248c6e8ff71d74949180eb3eba537cb42080d15fef88395725",
|
||||
"extraction_status": "text_indexed",
|
||||
"character_count": 633,
|
||||
"line_count": 27,
|
||||
"decode_replacement_count": 0,
|
||||
"classification": "research_governance",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "governance_or_history",
|
||||
"reason": "Research history or governance record; index separately from rule truth."
|
||||
},
|
||||
"docs/research/character_level_inventory_manifest_latest.json": {
|
||||
"path": "docs/research/character_level_inventory_manifest_latest.json",
|
||||
"suffix": ".json",
|
||||
"byte_count": 719007,
|
||||
"sha256": "b838192193044fda5ff7684778e26006c53be9892b9fafa70d7398641fbc2eed",
|
||||
"byte_count": 721667,
|
||||
"sha256": "aba3169d10fe86f02dfed264b150afb84473994225b2a62a36b720f485ad1a41",
|
||||
"extraction_status": "text_indexed",
|
||||
"character_count": 718457,
|
||||
"line_count": 15032,
|
||||
"character_count": 721117,
|
||||
"line_count": 15090,
|
||||
"decode_replacement_count": 0,
|
||||
"classification": "research_governance",
|
||||
"priority": "priority_3",
|
||||
@@ -5186,7 +5243,7 @@
|
||||
"path": "docs/research/character_level_inventory_manifest_latest.md",
|
||||
"suffix": ".md",
|
||||
"byte_count": 1090,
|
||||
"sha256": "19fb031f612b0747384eb3801abc1d19088a233fb662dde690817b5d686aa342",
|
||||
"sha256": "d088bb6312805a0f78506af37c2d32098e97af635eb3eed707a4943b75dae2ae",
|
||||
"extraction_status": "text_indexed",
|
||||
"character_count": 1090,
|
||||
"line_count": 44,
|
||||
@@ -15028,5 +15085,6 @@
|
||||
"artifacts": {
|
||||
"json_report": "docs/research/character_level_inventory_manifest_latest.json",
|
||||
"markdown_report": "docs/research/character_level_inventory_manifest_latest.md"
|
||||
}
|
||||
},
|
||||
"title": "Character-Level Inventory Manifest"
|
||||
}
|
||||
@@ -2,8 +2,8 @@
|
||||
|
||||
- status: pass
|
||||
- scope: project
|
||||
- generated_at: 2026-07-02T08:50:52.465261+00:00
|
||||
- total_files: 1069
|
||||
- generated_at: 2026-07-02T09:11:51.839696+00:00
|
||||
- total_files: 1073
|
||||
- unhashed_files: 0
|
||||
- unclassified_files: 0
|
||||
- unknown_extraction_status: 0
|
||||
@@ -16,7 +16,7 @@
|
||||
| --- | ---: | ---: |
|
||||
| `AGENTS.md` | 1 | 3932 |
|
||||
| `SKILL.md` | 1 | 43187 |
|
||||
| `docs/research` | 532 | 2198779 |
|
||||
| `docs/research` | 536 | 2901473 |
|
||||
| `references` | 236 | 4008411 |
|
||||
| `references/open_source_sources` | 299 | 9365015 |
|
||||
|
||||
@@ -24,7 +24,7 @@
|
||||
|
||||
- `binary_indexed`: 34
|
||||
- `image_ocr_queued`: 3
|
||||
- `text_indexed`: 1032
|
||||
- `text_indexed`: 1036
|
||||
|
||||
## Classification Counts
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
- `quarantined_draft`: 93
|
||||
- `real_case_calibration`: 5
|
||||
- `reference_candidate`: 180
|
||||
- `research_governance`: 439
|
||||
- `research_governance`: 443
|
||||
|
||||
## Boundary
|
||||
|
||||
|
||||
+15
@@ -805,3 +805,18 @@
|
||||
- 当前分类计数：`open_source_reference=299`、`reference_candidate=180`、`research_governance=439`、`quarantined_draft=93`、`real_case_calibration=5`、`oracle_artifact=51`、`project_governance=2`。
|
||||
- 当前提取状态：`text_indexed=1032`、`binary_indexed=34`、`image_ocr_queued=3`；本轮为省算力模式，未跑重 OCR，也未跑全机器长扫描。
|
||||
- 新增 `tests/test_character_level_inventory_manifest.py`，并把 manifest gate 接入 `scripts/run_quality_gate.py`；质量门使用 `--no-write --summary-only`，避免 CI 反复刷新报告或打印全量 `by_path`。
|
||||
|
||||
## 2026-07-02T17:08:00+08:00 - 外部高相关资料 manifest 第一阶段
|
||||
|
||||
- 扩展 `scripts/character_level_inventory_manifest.py --scope external`，只扫高相关外部路径，不做全机器深扫，不复制私人正文进仓库。
|
||||
- 新增 `docs/research/character_level_external_manifest_latest.json` 与 `.md`，当前覆盖 `883` 个外部高相关文件：`unhashed_files=0`、`unclassified_files=0`、`unknown_extraction_status=0`。
|
||||
- 外部来源桶：`~/.workbuddy=767`、`~/文件仓库=43`、`~/WorkBuddy=36`、`~/Downloads=15`、`~/Documents/ObsidianVault=11`、`~/engines-repo=6`、`~/Desktop=5`。
|
||||
- 外部提取状态：`text_indexed=735`、`text_decode_lossy=2`、`pdf_text_extraction_queued=2`、`document_text_extraction_queued=11`、`image_ocr_queued=50`、`binary_indexed=83`。
|
||||
- 外部分级：`external_skill_fragment=767`、`external_book_or_document=46`、`external_historical_report=37`、`external_engine_fragment=10`、`external_archive_or_binary=23`；均为 index/reference 阶段，不进入 runtime truth chain。
|
||||
|
||||
## 2026-07-02T17:11:00+08:00 - PDF/图片/文档提取队列 manifest
|
||||
|
||||
- 新增 `scripts/character_level_inventory_manifest.py --scope extraction-queue`，把项目内与外部 manifest 中的 PDF / 图片 / Office 文档待提取项合并为单独队列。
|
||||
- 新增 `docs/research/character_level_extraction_queue_latest.json` 与 `.md`，当前 queued_files=`66`、`unhashed_files=0`。
|
||||
- 队列构成：`image_ocr_queued=53`、`document_text_extraction_queued=11`、`pdf_text_extraction_queued=2`；来源为 `external=63`、`project=3`。
|
||||
- 边界：本轮只做提取队列，不跑重 OCR，不把外部私人资料正文写进仓库，也不升格为 runtime truth。
|
||||
|
||||
@@ -20,6 +20,10 @@ from typing import Any
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
REPORT_JSON = ROOT / "docs" / "research" / "character_level_inventory_manifest_latest.json"
|
||||
REPORT_MD = ROOT / "docs" / "research" / "character_level_inventory_manifest_latest.md"
|
||||
EXTERNAL_REPORT_JSON = ROOT / "docs" / "research" / "character_level_external_manifest_latest.json"
|
||||
EXTERNAL_REPORT_MD = ROOT / "docs" / "research" / "character_level_external_manifest_latest.md"
|
||||
EXTRACTION_QUEUE_JSON = ROOT / "docs" / "research" / "character_level_extraction_queue_latest.json"
|
||||
EXTRACTION_QUEUE_MD = ROOT / "docs" / "research" / "character_level_extraction_queue_latest.md"
|
||||
|
||||
PROJECT_SCAN_ROOTS = [
|
||||
"references",
|
||||
@@ -29,6 +33,36 @@ PROJECT_SCAN_ROOTS = [
|
||||
"AGENTS.md",
|
||||
]
|
||||
|
||||
EXTERNAL_SCAN_ROOTS = [
|
||||
Path.home() / "Downloads",
|
||||
Path.home() / "Desktop",
|
||||
Path.home() / "文件仓库" / "印度占星文章",
|
||||
Path.home() / ".workbuddy" / "skills" / "jyotish-vedic-astrology",
|
||||
Path.home() / "WorkBuddy" / "2026-06-09-20-03-34" / "jyotish-fragments",
|
||||
Path.home() / "WorkBuddy" / "2026-06-10-21-30-47",
|
||||
Path.home() / "WorkBuddy" / "2026-06-12-15-22-12",
|
||||
Path.home() / "WorkBuddy" / "20260422235041",
|
||||
Path.home() / "WorkBuddy" / "20260503121822",
|
||||
Path.home() / "WorkBuddy" / "engines-repo" / "jyotish",
|
||||
Path.home() / "engines-repo" / "jyotish",
|
||||
Path.home() / "Documents" / "ObsidianVault" / "03_研究_术数占星",
|
||||
]
|
||||
|
||||
EXTERNAL_KEYWORDS = [
|
||||
"印度占星",
|
||||
"占星",
|
||||
"jyotish",
|
||||
"vedic",
|
||||
"astrology",
|
||||
"jhora",
|
||||
"pyjhora",
|
||||
"vedastro",
|
||||
"dasha",
|
||||
"shadbala",
|
||||
"tajika",
|
||||
"jaimini",
|
||||
]
|
||||
|
||||
EXCLUDED_PARTS = {
|
||||
".git",
|
||||
".pytest_cache",
|
||||
@@ -65,6 +99,11 @@ TEXT_EXTENSIONS = {
|
||||
PDF_EXTENSIONS = {".pdf"}
|
||||
IMAGE_EXTENSIONS = {".bmp", ".gif", ".jpeg", ".jpg", ".png", ".tif", ".tiff", ".webp"}
|
||||
DOCUMENT_EXTENSIONS = {".doc", ".docx", ".epub", ".mobi", ".pages", ".ppt", ".pptx", ".rtf", ".xls", ".xlsx"}
|
||||
QUEUED_EXTRACTION_STATUSES = {
|
||||
"pdf_text_extraction_queued",
|
||||
"image_ocr_queued",
|
||||
"document_text_extraction_queued",
|
||||
}
|
||||
|
||||
|
||||
def _relative(path: Path) -> str:
|
||||
@@ -92,6 +131,26 @@ def _iter_project_files() -> list[Path]:
|
||||
return sorted(files)
|
||||
|
||||
|
||||
def _is_external_relevant(path: Path) -> bool:
|
||||
lowered = str(path).lower()
|
||||
return any(keyword.lower() in lowered for keyword in EXTERNAL_KEYWORDS)
|
||||
|
||||
|
||||
def _iter_external_files() -> list[Path]:
|
||||
files: set[Path] = set()
|
||||
for root in EXTERNAL_SCAN_ROOTS:
|
||||
if not root.exists() or _should_skip(root):
|
||||
continue
|
||||
if root.is_file():
|
||||
if _is_external_relevant(root):
|
||||
files.add(root)
|
||||
continue
|
||||
for path in root.rglob("*"):
|
||||
if path.is_file() and not _should_skip(path) and _is_external_relevant(path):
|
||||
files.add(path)
|
||||
return sorted(files)
|
||||
|
||||
|
||||
def _sha256(path: Path) -> str:
|
||||
digest = hashlib.sha256()
|
||||
with path.open("rb") as handle:
|
||||
@@ -220,10 +279,74 @@ def _root_bucket(path: str) -> str:
|
||||
return path.split("/", 1)[0]
|
||||
|
||||
|
||||
def build_manifest(*, scope: str = "project", write: bool = True) -> dict[str, Any]:
|
||||
if scope != "project":
|
||||
raise ValueError("Only --scope project is supported by the lightweight manifest.")
|
||||
def _external_path(path: Path) -> str:
|
||||
return str(path)
|
||||
|
||||
|
||||
def _classify_external_path(path: str) -> dict[str, str]:
|
||||
suffix = Path(path).suffix.lower()
|
||||
if "/.workbuddy/skills/jyotish-vedic-astrology/" in path:
|
||||
return {
|
||||
"classification": "external_skill_fragment",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_candidate",
|
||||
"reason": "External Jyotish skill copy; index only until diffed against repo truth.",
|
||||
}
|
||||
if "/engines-repo/jyotish/" in path or "/WorkBuddy/engines-repo/jyotish/" in path:
|
||||
return {
|
||||
"classification": "external_engine_fragment",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_candidate",
|
||||
"reason": "External engine fragment; requires source diff and license boundary review.",
|
||||
}
|
||||
if "/WorkBuddy/" in path or "/Desktop/" in path:
|
||||
return {
|
||||
"classification": "external_historical_report",
|
||||
"priority": "priority_2",
|
||||
"promotion_status": "external_reference_only",
|
||||
"reason": "Historical report or work artifact; do not promote without privacy review.",
|
||||
}
|
||||
if suffix in PDF_EXTENSIONS or suffix in DOCUMENT_EXTENSIONS or "/文件仓库/印度占星文章/" in path:
|
||||
return {
|
||||
"classification": "external_book_or_document",
|
||||
"priority": "priority_1",
|
||||
"promotion_status": "external_reference_only",
|
||||
"reason": "External book/document source; requires extraction and source grading before use.",
|
||||
}
|
||||
return {
|
||||
"classification": "external_archive_or_binary",
|
||||
"priority": "priority_3",
|
||||
"promotion_status": "external_index_only",
|
||||
"reason": "External relevant asset; indexed without content promotion.",
|
||||
}
|
||||
|
||||
|
||||
def _external_root_bucket(path: str) -> str:
|
||||
home = str(Path.home())
|
||||
if path.startswith(home + "/Downloads/"):
|
||||
return "~/Downloads"
|
||||
if path.startswith(home + "/Desktop/"):
|
||||
return "~/Desktop"
|
||||
if path.startswith(home + "/文件仓库/"):
|
||||
return "~/文件仓库"
|
||||
if path.startswith(home + "/.workbuddy/"):
|
||||
return "~/.workbuddy"
|
||||
if path.startswith(home + "/WorkBuddy/"):
|
||||
return "~/WorkBuddy"
|
||||
if path.startswith(home + "/engines-repo/"):
|
||||
return "~/engines-repo"
|
||||
if path.startswith(home + "/Documents/ObsidianVault/"):
|
||||
return "~/Documents/ObsidianVault"
|
||||
return path
|
||||
|
||||
|
||||
def _build_index(
|
||||
*,
|
||||
files: list[Path],
|
||||
path_label,
|
||||
classify,
|
||||
root_bucket,
|
||||
) -> tuple[dict[str, dict[str, Any]], dict[str, Any], dict[str, dict[str, int]]]:
|
||||
by_path: dict[str, dict[str, Any]] = {}
|
||||
classification_counts: dict[str, int] = {}
|
||||
extraction_counts: dict[str, int] = {}
|
||||
@@ -231,9 +354,9 @@ def build_manifest(*, scope: str = "project", write: bool = True) -> dict[str, A
|
||||
unclassified_files = 0
|
||||
unknown_extraction_status = 0
|
||||
|
||||
for file_path in _iter_project_files():
|
||||
rel = _relative(file_path)
|
||||
file_class = _classify_path(rel)
|
||||
for file_path in files:
|
||||
rel = path_label(file_path)
|
||||
file_class = classify(rel)
|
||||
extraction = _extraction_status(file_path)
|
||||
if not file_class.get("classification"):
|
||||
unclassified_files += 1
|
||||
@@ -251,7 +374,7 @@ def build_manifest(*, scope: str = "project", write: bool = True) -> dict[str, A
|
||||
by_path[rel] = item
|
||||
classification_counts[item["classification"]] = classification_counts.get(item["classification"], 0) + 1
|
||||
extraction_counts[item["extraction_status"]] = extraction_counts.get(item["extraction_status"], 0) + 1
|
||||
bucket = _root_bucket(rel)
|
||||
bucket = root_bucket(rel)
|
||||
root_summary.setdefault(bucket, {"files": 0, "bytes": 0})
|
||||
root_summary[bucket]["files"] += 1
|
||||
root_summary[bucket]["bytes"] += byte_count
|
||||
@@ -264,41 +387,148 @@ def build_manifest(*, scope: str = "project", write: bool = True) -> dict[str, A
|
||||
"classification_counts": dict(sorted(classification_counts.items())),
|
||||
"extraction_status_counts": dict(sorted(extraction_counts.items())),
|
||||
}
|
||||
status = "pass" if summary["unhashed_files"] == 0 and unclassified_files == 0 and unknown_extraction_status == 0 else "fail"
|
||||
return by_path, summary, dict(sorted(root_summary.items()))
|
||||
|
||||
|
||||
def build_manifest(*, scope: str = "project", write: bool = True) -> dict[str, Any]:
|
||||
if scope == "project":
|
||||
files = _iter_project_files()
|
||||
path_label = _relative
|
||||
classify = _classify_path
|
||||
root_bucket = _root_bucket
|
||||
scan_roots = PROJECT_SCAN_ROOTS
|
||||
json_report = REPORT_JSON
|
||||
markdown_report = REPORT_MD
|
||||
title = "Character-Level Inventory Manifest"
|
||||
mode = {
|
||||
"heavy_ocr": False,
|
||||
"whole_machine_scan": False,
|
||||
"external_high_relevance_scan": False,
|
||||
"semantic_promotion": False,
|
||||
"boundary": "Fast manifest only: hashes and cheap text stats now; heavy OCR and whole-machine scan are queued.",
|
||||
}
|
||||
elif scope == "external":
|
||||
files = _iter_external_files()
|
||||
path_label = _external_path
|
||||
classify = _classify_external_path
|
||||
root_bucket = _external_root_bucket
|
||||
scan_roots = [str(path) for path in EXTERNAL_SCAN_ROOTS]
|
||||
json_report = EXTERNAL_REPORT_JSON
|
||||
markdown_report = EXTERNAL_REPORT_MD
|
||||
title = "External High-Relevance Inventory Manifest"
|
||||
mode = {
|
||||
"heavy_ocr": False,
|
||||
"whole_machine_scan": False,
|
||||
"external_high_relevance_scan": True,
|
||||
"semantic_promotion": False,
|
||||
"boundary": "External scan is high-relevance only. It records hashes and extraction states without copying private source text into repo truth.",
|
||||
}
|
||||
elif scope == "extraction-queue":
|
||||
return build_extraction_queue(write=write)
|
||||
else:
|
||||
raise ValueError(f"Unsupported scope: {scope}")
|
||||
|
||||
by_path, summary, root_summary = _build_index(
|
||||
files=files,
|
||||
path_label=path_label,
|
||||
classify=classify,
|
||||
root_bucket=root_bucket,
|
||||
)
|
||||
status = (
|
||||
"pass"
|
||||
if summary["unhashed_files"] == 0
|
||||
and summary["unclassified_files"] == 0
|
||||
and summary["unknown_extraction_status"] == 0
|
||||
else "fail"
|
||||
)
|
||||
report = {
|
||||
"scope": scope,
|
||||
"status": status,
|
||||
"generated_at": datetime.now(timezone.utc).isoformat(),
|
||||
"mode": {
|
||||
"heavy_ocr": False,
|
||||
"whole_machine_scan": False,
|
||||
"semantic_promotion": False,
|
||||
"boundary": "Fast manifest only: hashes and cheap text stats now; heavy OCR and whole-machine scan are queued.",
|
||||
},
|
||||
"scan_roots": PROJECT_SCAN_ROOTS,
|
||||
"mode": mode,
|
||||
"scan_roots": scan_roots,
|
||||
"summary": summary,
|
||||
"root_summary": dict(sorted(root_summary.items())),
|
||||
"root_summary": root_summary,
|
||||
"by_path": by_path,
|
||||
"artifacts": {
|
||||
"json_report": _relative(REPORT_JSON),
|
||||
"markdown_report": _relative(REPORT_MD),
|
||||
"json_report": _relative(json_report),
|
||||
"markdown_report": _relative(markdown_report),
|
||||
},
|
||||
"title": title,
|
||||
}
|
||||
if write:
|
||||
_write_reports(report)
|
||||
_write_reports(report, json_report=json_report, markdown_report=markdown_report)
|
||||
return report
|
||||
|
||||
|
||||
def _write_reports(report: dict[str, Any]) -> None:
|
||||
REPORT_JSON.parent.mkdir(parents=True, exist_ok=True)
|
||||
REPORT_JSON.write_text(json.dumps(report, ensure_ascii=False, indent=2), encoding="utf-8")
|
||||
REPORT_MD.write_text(_render_markdown(report), encoding="utf-8")
|
||||
def build_extraction_queue(*, write: bool = True) -> dict[str, Any]:
|
||||
project = build_manifest(scope="project", write=False)
|
||||
external = build_manifest(scope="external", write=False)
|
||||
queue: list[dict[str, Any]] = []
|
||||
for source_scope, manifest in [("project", project), ("external", external)]:
|
||||
for item in manifest["by_path"].values():
|
||||
if item["extraction_status"] not in QUEUED_EXTRACTION_STATUSES:
|
||||
continue
|
||||
queue.append(
|
||||
{
|
||||
"source_scope": source_scope,
|
||||
"path": item["path"],
|
||||
"suffix": item["suffix"],
|
||||
"byte_count": item["byte_count"],
|
||||
"sha256": item["sha256"],
|
||||
"extraction_status": item["extraction_status"],
|
||||
"classification": item["classification"],
|
||||
"priority": item["priority"],
|
||||
"promotion_status": item["promotion_status"],
|
||||
}
|
||||
)
|
||||
queue.sort(key=lambda item: (item["extraction_status"], item["source_scope"], item["path"]))
|
||||
queue_counts: dict[str, int] = {}
|
||||
source_counts: dict[str, int] = {}
|
||||
for item in queue:
|
||||
queue_counts[item["extraction_status"]] = queue_counts.get(item["extraction_status"], 0) + 1
|
||||
source_counts[item["source_scope"]] = source_counts.get(item["source_scope"], 0) + 1
|
||||
report = {
|
||||
"scope": "extraction-queue",
|
||||
"status": "pass",
|
||||
"generated_at": datetime.now(timezone.utc).isoformat(),
|
||||
"mode": {
|
||||
"heavy_ocr": False,
|
||||
"whole_machine_scan": False,
|
||||
"external_high_relevance_scan": True,
|
||||
"semantic_promotion": False,
|
||||
"boundary": "Queue only. It identifies PDF/image/document extraction work without performing OCR or promoting extracted text.",
|
||||
},
|
||||
"summary": {
|
||||
"queued_files": len(queue),
|
||||
"unhashed_files": sum(1 for item in queue if not item.get("sha256")),
|
||||
"source_counts": dict(sorted(source_counts.items())),
|
||||
},
|
||||
"queue_counts": dict(sorted(queue_counts.items())),
|
||||
"queue": queue,
|
||||
"artifacts": {
|
||||
"json_report": _relative(EXTRACTION_QUEUE_JSON),
|
||||
"markdown_report": _relative(EXTRACTION_QUEUE_MD),
|
||||
},
|
||||
"title": "Extraction Queue Manifest",
|
||||
}
|
||||
if write:
|
||||
_write_reports(report, json_report=EXTRACTION_QUEUE_JSON, markdown_report=EXTRACTION_QUEUE_MD)
|
||||
return report
|
||||
|
||||
|
||||
def _write_reports(report: dict[str, Any], *, json_report: Path, markdown_report: Path) -> None:
|
||||
json_report.parent.mkdir(parents=True, exist_ok=True)
|
||||
json_report.write_text(json.dumps(report, ensure_ascii=False, indent=2), encoding="utf-8")
|
||||
markdown_report.write_text(_render_markdown(report), encoding="utf-8")
|
||||
|
||||
|
||||
def _render_markdown(report: dict[str, Any]) -> str:
|
||||
summary = report["summary"]
|
||||
if report["scope"] == "extraction-queue":
|
||||
return _render_extraction_queue_markdown(report)
|
||||
lines = [
|
||||
"# Character-Level Inventory Manifest",
|
||||
f"# {report.get('title', 'Character-Level Inventory Manifest')}",
|
||||
"",
|
||||
f"- status: {report['status']}",
|
||||
f"- scope: {report['scope']}",
|
||||
@@ -337,6 +567,40 @@ def _render_markdown(report: dict[str, Any]) -> str:
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def _render_extraction_queue_markdown(report: dict[str, Any]) -> str:
|
||||
lines = [
|
||||
f"# {report.get('title', 'Extraction Queue Manifest')}",
|
||||
"",
|
||||
f"- status: {report['status']}",
|
||||
f"- scope: {report['scope']}",
|
||||
f"- generated_at: {report['generated_at']}",
|
||||
f"- queued_files: {report['summary']['queued_files']}",
|
||||
f"- unhashed_files: {report['summary']['unhashed_files']}",
|
||||
f"- Heavy OCR: {'enabled' if report['mode']['heavy_ocr'] else 'disabled'}",
|
||||
f"- Whole-machine scan: {'enabled' if report['mode']['whole_machine_scan'] else 'disabled'}",
|
||||
"",
|
||||
"## Queue Counts",
|
||||
"",
|
||||
]
|
||||
for name, count in report["queue_counts"].items():
|
||||
lines.append(f"- `{name}`: {count}")
|
||||
lines.extend(["", "## Source Counts", ""])
|
||||
for name, count in report["summary"]["source_counts"].items():
|
||||
lines.append(f"- `{name}`: {count}")
|
||||
lines.extend(
|
||||
[
|
||||
"",
|
||||
"## Boundary",
|
||||
"",
|
||||
report["mode"]["boundary"],
|
||||
"",
|
||||
"Queued files are indexed by path, size, hash, and extraction status only. Private source text is not copied into this report.",
|
||||
"",
|
||||
]
|
||||
)
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def _summary_view(report: dict[str, Any]) -> dict[str, Any]:
|
||||
return {
|
||||
key: value
|
||||
@@ -347,7 +611,7 @@ def _summary_view(report: dict[str, Any]) -> dict[str, Any]:
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument("--scope", default="project", choices=["project"])
|
||||
parser.add_argument("--scope", default="project", choices=["project", "external", "extraction-queue"])
|
||||
parser.add_argument("--no-write", action="store_true", help="Print the manifest without writing report artifacts.")
|
||||
parser.add_argument("--summary-only", action="store_true", help="Print only summary fields; still writes full artifacts unless --no-write is set.")
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
@@ -99,3 +99,80 @@ def test_quality_gate_runs_character_level_manifest_without_writing_reports() ->
|
||||
'[PYTHON, "scripts/character_level_inventory_manifest.py", "--scope", "project", "--no-write", "--summary-only"]'
|
||||
in quality_gate
|
||||
)
|
||||
|
||||
|
||||
def test_external_manifest_indexes_high_relevance_machine_fragments_without_copying_text() -> None:
|
||||
report = _run_manifest("--scope", "external", "--no-write")
|
||||
|
||||
assert report["scope"] == "external"
|
||||
assert report["status"] == "pass"
|
||||
assert report["mode"]["whole_machine_scan"] is False
|
||||
assert report["mode"]["external_high_relevance_scan"] is True
|
||||
assert report["summary"]["total_files"] >= 10
|
||||
assert report["summary"]["unhashed_files"] == 0
|
||||
assert report["summary"]["unclassified_files"] == 0
|
||||
assert report["summary"]["unknown_extraction_status"] == 0
|
||||
|
||||
paths = set(report["by_path"])
|
||||
assert any(path.endswith("/Downloads/印度占星.pdf") for path in paths)
|
||||
assert any("/文件仓库/印度占星文章/" in path for path in paths)
|
||||
assert any("/WorkBuddy/" in path for path in paths)
|
||||
assert any("/.workbuddy/skills/jyotish-vedic-astrology/" in path for path in paths)
|
||||
|
||||
extraction_counts = report["summary"]["extraction_status_counts"]
|
||||
assert extraction_counts["pdf_text_extraction_queued"] >= 1
|
||||
assert extraction_counts["document_text_extraction_queued"] >= 1
|
||||
|
||||
for path, item in report["by_path"].items():
|
||||
assert path.startswith("/Users/wuyongnaren/")
|
||||
assert item["sha256"]
|
||||
assert item["classification"] in {
|
||||
"external_book_or_document",
|
||||
"external_engine_fragment",
|
||||
"external_historical_report",
|
||||
"external_skill_fragment",
|
||||
"external_archive_or_binary",
|
||||
}
|
||||
assert "text_preview" not in item
|
||||
|
||||
|
||||
def test_external_manifest_writes_separate_reports() -> None:
|
||||
report = _run_manifest("--scope", "external", "--summary-only")
|
||||
|
||||
assert "by_path" not in report
|
||||
assert report["artifacts"]["json_report"] == "docs/research/character_level_external_manifest_latest.json"
|
||||
assert report["artifacts"]["markdown_report"] == "docs/research/character_level_external_manifest_latest.md"
|
||||
|
||||
json_path = ROOT / report["artifacts"]["json_report"]
|
||||
md_path = ROOT / report["artifacts"]["markdown_report"]
|
||||
assert json_path.exists()
|
||||
assert md_path.exists()
|
||||
assert "External High-Relevance Inventory Manifest" in md_path.read_text(encoding="utf-8")
|
||||
|
||||
|
||||
def test_extraction_queue_report_combines_project_and_external_binary_work() -> None:
|
||||
report = _run_manifest("--scope", "extraction-queue")
|
||||
|
||||
assert report["scope"] == "extraction-queue"
|
||||
assert report["status"] == "pass"
|
||||
assert report["summary"]["queued_files"] >= 60
|
||||
assert report["summary"]["unhashed_files"] == 0
|
||||
assert report["queue_counts"]["pdf_text_extraction_queued"] >= 2
|
||||
assert report["queue_counts"]["document_text_extraction_queued"] >= 10
|
||||
assert report["queue_counts"]["image_ocr_queued"] >= 50
|
||||
|
||||
for item in report["queue"]:
|
||||
assert item["sha256"]
|
||||
assert item["source_scope"] in {"project", "external"}
|
||||
assert item["extraction_status"] in {
|
||||
"pdf_text_extraction_queued",
|
||||
"image_ocr_queued",
|
||||
"document_text_extraction_queued",
|
||||
}
|
||||
assert "text_preview" not in item
|
||||
|
||||
json_path = ROOT / report["artifacts"]["json_report"]
|
||||
md_path = ROOT / report["artifacts"]["markdown_report"]
|
||||
assert json_path.exists()
|
||||
assert md_path.exists()
|
||||
assert "Extraction Queue Manifest" in md_path.read_text(encoding="utf-8")
|
||||
|
||||
Reference in New Issue
Block a user