| .. |
|
__init__.py
|
feat(prune): core orphan paper cleanup module
|
2026-05-18 21:48:18 +08:00 |
|
_domain.py
|
chore: commit session work before hotfix switch
|
2026-05-18 22:47:30 +08:00 |
|
_progress.py
|
ocr rebuild: add --resume checkpoint, fix garbled progress bar, remove debug print
|
2026-06-26 17:31:52 +08:00 |
|
_retry.py
|
docs(v1.4): commit planning artifacts, test files, and phase summaries for phases 13-19
|
2026-04-27 19:12:03 +08:00 |
|
_utils.py
|
feat: ocr reading-order fixes, single-source fulltext, redo closed-loop, release notes & manual
|
2026-06-01 18:12:31 +08:00 |
|
asset_index.py
|
feat: P0 fixes (ref sort, caption insert) + P1 figure containment render hygiene
|
2026-06-27 22:56:22 +08:00 |
|
asset_state.py
|
style: ruff format pass across paperforge/
|
2026-05-09 22:31:08 +08:00 |
|
base_views.py
|
feat: PR D — Base view cleanup
|
2026-07-05 01:26:34 +08:00 |
|
deep_reading.py
|
test: lock OCR phase2 figure inventory contract
|
2026-06-05 00:08:30 +08:00 |
|
discussion.py
|
chore: commit session work before hotfix switch
|
2026-05-18 22:47:30 +08:00 |
|
ocr.py
|
feat: expose library OCR and memory capability tracers (#78)
|
2026-07-18 18:13:08 +08:00 |
|
ocr_artifacts.py
|
fix: close structural convergence gaps — primary-path frontmatter anchor, health spine alignment, unresolved figure clusters, artifact cache cleanup
|
2026-06-08 00:24:54 +08:00 |
|
ocr_attach.py
|
test: add OCR real-paper regression tests and cleanup
|
2026-06-10 12:36:15 +08:00 |
|
ocr_banding.py
|
feat: layout robustness layer — robust banding, role-aware gating, two-column continuation
|
2026-07-02 19:15:44 +08:00 |
|
ocr_bio.py
|
fix: backmatter_body (author bios) after refs in skip_section_grouping render
|
2026-06-29 14:10:50 +08:00 |
|
ocr_blocks.py
|
C0: add OCR_PIPELINE_V3 toggle, seed-only build_structured_blocks, stub modules
|
2026-07-04 15:54:53 +08:00 |
|
ocr_decisions.py
|
test: add OCR real-paper regression tests and cleanup
|
2026-06-10 12:36:15 +08:00 |
|
ocr_document.py
|
fix(pr3): remove same-column guard from body_blocks, fix _page_width_for_zone_block arg
|
2026-07-04 22:36:46 +08:00 |
|
ocr_emit.py
|
docs: audit OCR production route and mark experimental modules
|
2026-06-08 12:13:07 +08:00 |
|
ocr_errors.py
|
feat: classify OCR errors and degraded completions
|
2026-06-08 12:34:44 +08:00 |
|
ocr_evidence.py
|
feat: add OCR evidence objects and paper-context summary
|
2026-06-05 12:15:51 +08:00 |
|
ocr_families.py
|
fix: reference-zone ordering fixes (P0-P4)
|
2026-07-02 19:06:06 +08:00 |
|
ocr_figure_domain.py
|
fix: rescue single narrow side-caption figure layouts
|
2026-07-06 02:38:59 +08:00 |
|
ocr_figure_reader.py
|
fix: address 5 post-review issues in previous-page locator bridge
|
2026-06-29 18:37:26 +08:00 |
|
ocr_figure_vnext_accounting_pass.py
|
refactor(ocr): add pairing pass runner and figure domain module
|
2026-07-03 19:41:46 +08:00 |
|
ocr_figure_vnext_bundle_pass.py
|
fix: appendix numbering cross-cutting bugs (TABLE regex, int block_id, table alpha prefix, weak-caption tie-break)
|
2026-07-04 01:29:06 +08:00 |
|
ocr_figure_vnext_classic_seq_pass.py
|
refactor(ocr): add pairing pass runner and figure domain module
|
2026-07-03 19:41:46 +08:00 |
|
ocr_figure_vnext_composite_pass.py
|
refactor(ocr): add pairing pass runner and figure domain module
|
2026-07-03 19:41:46 +08:00 |
|
ocr_figure_vnext_corpus.py
|
refactor(ocr): add pairing pass runner and figure domain module
|
2026-07-03 19:41:46 +08:00 |
|
ocr_figure_vnext_group_seq_pass.py
|
fix: rescue single narrow side-caption figure layouts
|
2026-07-06 02:38:59 +08:00 |
|
ocr_figure_vnext_locator_pass.py
|
refactor(ocr): add pairing pass runner and figure domain module
|
2026-07-03 19:41:46 +08:00 |
|
ocr_figure_vnext_passes.py
|
fix: rescue single narrow side-caption figure layouts
|
2026-07-06 02:38:59 +08:00 |
|
ocr_figure_vnext_sidecar_pass.py
|
fix: two regression fixes
|
2026-07-06 02:49:42 +08:00 |
|
ocr_figure_vnext_state.py
|
refactor(ocr): extract generic pairing types and state from figure vnext
|
2026-07-03 19:39:44 +08:00 |
|
ocr_figure_vnext_types.py
|
refactor(ocr): extract generic pairing types and state from figure vnext
|
2026-07-03 19:39:44 +08:00 |
|
ocr_figures.py
|
fix: rescue single narrow side-caption figure layouts
|
2026-07-06 02:38:59 +08:00 |
|
ocr_fulltext_state.py
|
feat: add fulltext writeback state helpers
|
2026-07-05 16:45:31 +08:00 |
|
ocr_health.py
|
feat: improve vnext figure matching and split OCR status
|
2026-07-06 00:55:40 +08:00 |
|
ocr_index.py
|
fix: stabilize legacy OCR structure and metadata recovery
|
2026-06-05 13:34:43 +08:00 |
|
ocr_layout.py
|
test: add OCR real-paper regression tests and cleanup
|
2026-06-10 12:36:15 +08:00 |
|
ocr_maintenance.py
|
feat: Phase 0, 1, 3a — legacy OCR fix, ChromaDB migration, search bar UI
|
2026-07-10 00:02:02 +08:00 |
|
ocr_math.py
|
fix: add relational-operator spacing and Greek-letter preservation to math normalization
|
2026-06-06 17:19:33 +08:00 |
|
ocr_metadata.py
|
fix: reuse rebuild metadata and object extraction work
|
2026-06-22 22:15:25 +08:00 |
|
ocr_object_writeback.py
|
fix: guard contained figure claims by page
|
2026-07-04 17:30:14 +08:00 |
|
ocr_objects.py
|
fix: final cleanup before merge — stale test, helper, RGB safety
|
2026-07-05 21:36:17 +08:00 |
|
ocr_orchestrator.py
|
test: add OCR real-paper regression tests and cleanup
|
2026-06-10 12:36:15 +08:00 |
|
ocr_pairing_framework.py
|
refactor(ocr): add pairing pass runner and figure domain module
|
2026-07-03 19:41:46 +08:00 |
|
ocr_pairing_state.py
|
fix(ocr): unblock pairing framework merge
|
2026-07-03 22:50:15 +08:00 |
|
ocr_pairing_types.py
|
refactor(ocr): extend pairing framework surface for table resources
|
2026-07-03 20:05:39 +08:00 |
|
ocr_pdf_spans.py
|
perf: merge Phase 1+2a into single PDF pass, add _extract_lines_from_rawdict
|
2026-07-05 20:55:10 +08:00 |
|
ocr_post_match_normalize.py
|
test: add DWQQK2YB v3 parity gate
|
2026-07-04 18:33:32 +08:00 |
|
ocr_pre_match_normalize.py
|
C1: shadow normalize in pre_match_normalize + _match_role helpers
|
2026-07-04 16:02:55 +08:00 |
|
ocr_profiles.py
|
feat: partition OCR families inside zones
|
2026-06-09 17:49:52 +08:00 |
|
ocr_quality.py
|
fix(ocr-quality): contract polish — 4 P0/P1 fixes
|
2026-07-04 23:38:03 +08:00 |
|
ocr_quality_feedback.py
|
fix(ocr-quality): contract polish — 4 P0/P1 fixes
|
2026-07-04 23:38:03 +08:00 |
|
ocr_rebuild.py
|
feat: add streaming OCR rebuild progress
|
2026-07-14 18:05:49 +08:00 |
|
ocr_reference_signals.py
|
fix: complete reference detection fixes — 5 problem families
|
2026-07-03 01:46:27 +08:00 |
|
ocr_render.py
|
fix: heading→emitted events, backmatter→heading events, page-qualified keys
|
2026-07-06 18:19:17 +08:00 |
|
ocr_roles.py
|
fix: exclude table-owned media and inline figure body refs from figure matching
|
2026-07-05 22:36:17 +08:00 |
|
ocr_scores.py
|
fix: appendix numbering cross-cutting bugs (TABLE regex, int block_id, table alpha prefix, weak-caption tie-break)
|
2026-07-04 01:29:06 +08:00 |
|
ocr_signatures.py
|
fix: support Roman numeral and S-prefix table captions across roles/signatures/tables
|
2026-07-02 00:47:18 +08:00 |
|
ocr_structural_gate.py
|
fix: inline <table> HTML blocks incorrectly assigned to media_asset
|
2026-07-03 01:46:46 +08:00 |
|
ocr_table_domain.py
|
C1: shadow normalize in pre_match_normalize + _match_role helpers
|
2026-07-04 16:02:55 +08:00 |
|
ocr_table_passes.py
|
fix: appendix numbering cross-cutting bugs (TABLE regex, int block_id, table alpha prefix, weak-caption tie-break)
|
2026-07-04 01:29:06 +08:00 |
|
ocr_tables.py
|
fix: two regression fixes
|
2026-07-06 02:49:42 +08:00 |
|
ocr_tail_settlement.py
|
feat: Workstream B — OCR tail settlement extraction and report
|
2026-07-04 13:37:45 +08:00 |
|
ocr_versions.py
|
feat(#37): auto-backup fulltext before rebuild
|
2026-07-10 00:34:44 +08:00 |
|
paper_meta.py
|
chore: commit session work before hotfix switch
|
2026-05-18 22:47:30 +08:00 |
|
paper_resolver.py
|
chore: commit session work before hotfix switch
|
2026-05-18 22:47:30 +08:00 |
|
prune.py
|
fix(sync): avoid prune crash when optional deps are missing
|
2026-05-31 20:55:17 +08:00 |
|
repair.py
|
chore: commit session work before hotfix switch
|
2026-05-18 22:47:30 +08:00 |
|
status.py
|
feat(#81): Release N+1 owner cutover — Python 3.11+ gate, fail-closed dispatch
|
2026-07-19 14:32:12 +08:00 |
|
sync.py
|
feat: ocr reading-order fixes, single-source fulltext, redo closed-loop, release notes & manual
|
2026-06-01 18:12:31 +08:00 |
|
update.py
|
chore: commit session work before hotfix switch
|
2026-05-18 22:47:30 +08:00 |
|
vector_db.py
|
chore: commit session work before hotfix switch
|
2026-05-18 22:47:30 +08:00 |