@furongjun1999/dsh-memory 0.4.11 → 0.5.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +16 -16
- package/codebuddy/CODEBUDDY.md +11 -3
- package/codebuddy/README.md +92 -90
- package/codebuddy/mcp.json +27 -27
- package/docs/GBrain/345/217/257/345/200/237/351/211/264/347/202/271_/347/201/265/346/236/242/350/220/275/347/202/271/344/272/244/346/216/245_20260919.md +169 -169
- package/docs/Pi/345/217/257/345/255/246/344/271/240/344/274/230/347/202/271_/347/201/265/346/236/242/345/244/247/350/204/221/346/224/271/350/277/233/344/272/244/346/216/245_20260915.md +144 -144
- package/docs/README.md +142 -111
- package/docs/discipline/harnesses.yaml +244 -226
- package/docs/discipline/templates/full.md.tmpl +61 -61
- package/docs/discipline/templates/rules.mdc.tmpl +68 -0
- package/docs/discipline/templates/skill.md.tmpl +23 -23
- package/docs/eval/AGI/344/270/203/347/273/264/350/257/204/345/210/206/346/212/245/345/221/212_md_cg_v1.0.md +299 -299
- package/docs/eval/AGI/344/270/203/347/273/264/350/257/204/345/210/206/346/212/245/345/221/212_md_cg_v2.0.md +239 -239
- package/docs/eval//345/256/236/351/252/214/346/226/271/346/241/210_/345/255/246/344/271/240/351/227/255/347/216/257AB/344/270/216/346/250/252/350/257/204_v1.0.md +174 -174
- package/docs/eval//346/250/252/350/257/204_/345/205/255/345/256/266100/351/242/230/344/270/255/350/213/261/345/217/214/346/237/245_v1.0.md +223 -223
- package/docs/{mdcg → hive}//344/273/244/347/211/214/344/270/216/350/247/222/350/211/262/346/235/203/350/201/214/345/210/206/347/246/273_v0.1.md +165 -160
- package/docs/hive//344/273/244/347/211/214/350/257/255/344/271/211/344/277/256/346/255/243_/344/273/262/350/243/201/344/275/215_v0.1.md +76 -0
- package/docs/{mdcg → hive}//345/255/220/344/273/243/347/220/206/351/205/215/347/275/256/346/240/207/345/207/206_v0.5.md +236 -236
- package/docs/hive//346/243/200/347/264/242/346/224/266/346/225/233/345/256/236/346/265/213/344/270/216S1b/350/256/276/350/256/241_v0.1.md +43 -43
- package/docs/hive//346/243/200/347/264/242/347/256/227/346/263/225/345/217/243/345/276/204/345/257/271/347/205/247_v0.1.md +85 -0
- package/docs/hive//346/243/200/347/264/242/350/267/257/345/276/204/344/270/216/350/256/244/347/237/245/347/273/223/346/236/204/345/245/221/347/272/246_v0.1.md +102 -102
- package/docs/hive//350/234/202/345/267/242M6_ingest/345/256/236/346/226/275/350/256/241/345/210/222_v0.1.md +47 -0
- package/docs/hive//350/234/202/345/267/242/345/217/214/345/256/236/344/276/213/344/272/222/351/252/214_/350/256/276/350/256/241/345/256/232/347/250/277.md +503 -503
- package/docs/hive//350/234/202/345/267/242/345/267/245/344/275/234/350/256/260/345/277/206_/351/241/271/347/233/256/350/256/241/345/210/222.md +85 -85
- package/docs/hive//350/234/202/345/267/242/350/256/276/350/256/241_/347/220/206/350/256/272/345/257/271/351/275/220_v0.1.md +191 -0
- package/docs/hive//350/234/202/345/267/242/350/277/255/344/273/243_/345/256/217/350/247/202/344/270/216/347/276/244/344/275/223/350/260/203/345/272/246_v0.1.md +90 -0
- package/docs/mdcg/D_meta_/345/267/245/347/250/213/345/214/226/346/226/271/346/241/210_v0.2.md +216 -216
- package/docs/mdcg/README/350/257/246/347/273/206/347/211/210_v0.4.10.md +646 -646
- package/docs/mdcg/lingshu_tutorial.html +14449 -14449
- package/docs/mdcg/release_v0.4.11.md +49 -0
- package/docs/mdcg/release_v0.4.5.md +55 -55
- package/docs/mdcg/tool_table_v0.3.0.md +117 -117
- package/docs/mdcg//345/205/250/345/272/223/344/273/243/347/240/201/350/257/204/345/256/241/344/270/216/346/235/241/344/273/266/345/214/226/346/263/250/351/207/212_/350/256/241/345/210/222_v0.1.md +600 -600
- package/docs/mdcg//345/212/237/350/203/275/350/260/203/347/224/250/346/230/240/345/260/204/350/241/250_v0.1.md +40 -40
- package/docs/mdcg//345/215/225/345/205/203/350/207/252/346/210/221/351/224/232/347/202/271_/347/263/273/347/273/237/346/217/220/347/244/272/350/257/215/346/240/207/345/207/206_v0.3.md +275 -275
- package/docs/mdcg//345/217/221/345/270/203/351/227/250/347/246/201/351/223/276_v0.1.md +54 -0
- package/docs/mdcg//346/272/220/347/240/201/347/272/247/346/236/266/346/236/204/345/256/241/350/256/241_GPT/346/211/271/350/257/204/345/257/271/347/205/247_v1.0.md +130 -130
- package/docs/mdcg//347/201/265/346/236/24282/345/267/245/345/205/267_/345/212/237/350/203/275/346/225/264/347/220/206/344/270/216/350/277/201/347/247/273/346/230/240/345/260/204_v0.1.md +278 -278
- package/docs/mdcg//347/201/265/346/236/242/350/256/260/345/277/206/345/212/250/350/257/215/345/215/217/350/256/256_v1.0-draft.md +172 -172
- package/docs/mdcg//347/274/272/345/217/243/345/215/225_P0/346/224/266/345/217/243_v0.1.md +270 -270
- package/docs/mdcg//350/256/244/347/237/245/345/233/276_G4-G8/347/274/272/345/217/243/350/243/201/345/256/232/345/215/225_v0.1.md +491 -491
- package/docs/mdcg//350/256/244/347/237/245/345/233/276_/346/235/241/344/273/266/347/251/272/351/227/264/345/220/210/346/210/220/344/270/216/347/224/237/346/225/210/346/235/241/344/273/266/345/217/243/345/276/204_v0.1.md +340 -340
- package/docs/mdcg//350/256/244/347/237/245/345/233/276_/347/264/242/345/274/225/344/270/216/345/267/245/347/250/213/350/247/204/350/214/203/345/214/226_/350/256/241/345/210/222_v0.1.md +588 -588
- package/docs/plans/GridWorld/346/234/200/345/260/217/351/227/255/347/216/257/350/247/204/346/240/274_v0.1.md +176 -176
- package/docs/plans//345/221/275/345/220/215/346/262/273/347/220/206_/351/241/271/347/233/256/350/256/241/345/210/222.md +81 -81
- package/docs/swarm//350/234/202/347/276/244/344/272/222/350/201/224_v0.1.md +704 -704
- package/docs/swarm//350/234/202/347/276/244/345/220/214/351/224/231/346/243/200/346/265/213/345/256/236/351/252/214/345/215/217/350/256/256_v0.1.md +242 -242
- package/docs/theory//345/215/225/347/272/277/347/250/213/344/270/216/346/263/250/346/204/217/345/212/233/351/233/206/344/270/255_/346/227/240/344/272/211/350/256/256/347/220/206/350/256/272/346/226/207/346/241/243_v1.0.md +129 -129
- package/docs/theory//345/271/266/345/217/221/345/277/205/347/204/266/346/200/247/347/220/206/350/256/272_v0.2.md +134 -134
- package/docs/theory//346/231/272/350/203/275/350/256/2723.4.md +5260 -5260
- package/docs/theory//346/246/202/345/277/265/345/210/206/345/261/202/345/257/271/351/275/220/350/241/250_v0.1.md +145 -145
- package/docs/theory//347/220/206/350/256/272_/346/234/272/345/210/266_/344/273/243/347/240/201_/345/256/236/351/252/214_/347/274/272/345/217/243/347/237/251/351/230/265_v0.1.md +144 -144
- package/docs/theory//347/220/206/350/256/272/344/273/223/346/213/206/345/210/206/344/270/216/347/231/275/347/256/261/347/237/245/350/257/206/345/272/223/345/206/205/350/277/201_v0.1.md +198 -198
- package/docs/theory//350/256/244/347/237/245/344/273/243/347/220/206/344/270/216/346/224/266/346/225/233/347/273/223/346/236/204_/346/235/241/344/273/266/350/256/272/351/207/215/346/236/204_v0.1.md +221 -221
- package/docs/world_model//344/270/226/347/225/214/346/250/241/345/236/213_/347/245/236/347/273/217/347/275/221/347/273/234/345/272/225/345/261/202/346/236/266/346/236/204_v1.0.md +237 -237
- package/docs//345/217/221/345/270/203/344/273/266/345/233/236/346/272/257/350/257/264/346/230/216_v0.1.md +82 -82
- package/docs//345/267/245/344/275/234/347/272/252/345/276/213_/350/256/244/347/237/245/345/233/276/346/235/241/347/233/256_v1.1.json +28 -2
- package/dsh/README.md +82 -82
- package/dsh/cordis.yml.example +139 -139
- package/dsh/update-lingshu.bat +11 -11
- package/lib/hooks.js +36 -2
- package/lib/lib/roleplay_web.js +427 -427
- package/md_cg/__init__.py +7 -7
- package/md_cg/audit.py +368 -368
- package/md_cg/autonomy.py +287 -287
- package/md_cg/backfill.py +1327 -1327
- package/md_cg/backfill_bigdomain.py +34 -34
- package/md_cg/bench6_arms.py +410 -410
- package/md_cg/bench6_common.py +230 -230
- package/md_cg/bench6_competitors.py +212 -212
- package/md_cg/bench_axis_domain.py +257 -257
- package/md_cg/bench_blind_comp.py +308 -308
- package/md_cg/bench_en_atoms_public.py +230 -230
- package/md_cg/bench_governance.py +348 -348
- package/md_cg/bench_lme_zh.py +410 -410
- package/md_cg/bench_locomo.py +121 -121
- package/md_cg/bench_locomo_zh.py +450 -450
- package/md_cg/bench_locomo_zh_public.py +147 -147
- package/md_cg/bench_longmem.py +112 -112
- package/md_cg/bench_membench.py +632 -632
- package/md_cg/bench_p0.py +149 -149
- package/md_cg/bench_progressive.py +287 -287
- package/md_cg/bench_role_views.py +238 -238
- package/md_cg/bench_task_ab.py +243 -243
- package/md_cg/bench_task_ab_llm.py +408 -408
- package/md_cg/bench_unified_en.py +204 -204
- package/md_cg/bench_zh_mad.py +601 -601
- package/md_cg/blindspot_tickets.py +123 -123
- package/md_cg/branches.py +285 -285
- package/md_cg/build_postings.py +73 -73
- package/md_cg/ccgc.py +1005 -948
- package/md_cg/census.py +132 -132
- package/md_cg/chain.py +300 -300
- package/md_cg/codeindex.py +531 -531
- package/md_cg/coldverify.py +292 -292
- package/md_cg/comment_gate.py +337 -337
- package/md_cg/cond_compose.py +190 -190
- package/md_cg/cond_facts.py +154 -154
- package/md_cg/cond_template.json +106 -106
- package/md_cg/condition_anchor.py +142 -142
- package/md_cg/conformance.py +726 -726
- package/md_cg/consistency.py +717 -717
- package/md_cg/consolidate.py +1536 -1439
- package/md_cg/corpus.py +110 -110
- package/md_cg/crosscheck.py +1097 -1097
- package/md_cg/crypto.py +437 -437
- package/md_cg/d_meta.py +310 -310
- package/md_cg/datapath.py +334 -334
- package/md_cg/docindex.py +473 -473
- package/md_cg/eval_common.py +575 -575
- package/md_cg/evidence.py +580 -580
- package/md_cg/evolution.py +477 -477
- package/md_cg/export.py +220 -220
- package/md_cg/forgetting.py +581 -581
- package/md_cg/fsutil.py +329 -329
- package/md_cg/hotcache.py +238 -214
- package/md_cg/hyperedge.py +251 -251
- package/md_cg/identity.py +390 -390
- package/md_cg/insight.py +500 -500
- package/md_cg/interop.py +199 -0
- package/md_cg/lexicon/build_cedict_en_zh.py +329 -329
- package/md_cg/lexicon/build_standard_en.py +171 -171
- package/md_cg/lexicon/expand_en_zh.py +211 -211
- package/md_cg/lifecycle.py +272 -272
- package/md_cg/linkref.py +280 -280
- package/md_cg/links.py +622 -622
- package/md_cg/mcp_server.py +129 -32
- package/md_cg/md_whitebox.py +345 -345
- package/md_cg/mdcg.py +176 -117
- package/md_cg/mdcos.py +79 -13
- package/md_cg/metacognition.py +591 -591
- package/md_cg/migrate.py +119 -119
- package/md_cg/migrate_aeis.py +221 -221
- package/md_cg/migrate_roleplay.py +293 -293
- package/md_cg/migrate_wisdom_graph.py +360 -360
- package/md_cg/mreview/__init__.py +25 -25
- package/md_cg/mreview/__main__.py +110 -110
- package/md_cg/mreview/bundle.py +178 -178
- package/md_cg/mreview/candidates.py +262 -262
- package/md_cg/mreview/govern.py +693 -693
- package/md_cg/mreview/locate.py +939 -939
- package/md_cg/mreview/pipeline.py +728 -728
- package/md_cg/mreview/rules/duplication.json +21 -21
- package/md_cg/mreview/rules/field_coverage.json +54 -54
- package/md_cg/mreview/rules/source_license.json +21 -21
- package/md_cg/mreview/rules/template_flow.json +21 -21
- package/md_cg/mreview/ruleset.py +252 -252
- package/md_cg/nodefile.py +575 -575
- package/md_cg/pooling.py +484 -472
- package/md_cg/postings.py +298 -298
- package/md_cg/predict.py +1100 -1100
- package/md_cg/progressive.py +123 -123
- package/md_cg/protect.py +272 -272
- package/md_cg/protocol/md_cg_gate.proto +33 -33
- package/md_cg/protocol.py +372 -372
- package/md_cg/provenance.py +582 -582
- package/md_cg/reach.py +453 -453
- package/md_cg/readcache.py +85 -0
- package/md_cg/refindex.py +833 -833
- package/md_cg/refine.py +604 -604
- package/md_cg/roleviews.py +89 -89
- package/md_cg/routing.py +365 -365
- package/md_cg/scrub.py +852 -852
- package/md_cg/security.py +274 -274
- package/md_cg/self_state.py +1029 -1029
- package/md_cg/selfreport.py +151 -151
- package/md_cg/semantic/__init__.py +10 -10
- package/md_cg/semantic/canonical.py +122 -122
- package/md_cg/semantic/en_normalizer.py +364 -364
- package/md_cg/semantic/en_zh_map.json +28694 -0
- package/md_cg/semantic/export_en_zh_map.py +64 -0
- package/md_cg/semantic/unify.py +45 -0
- package/md_cg/semantic/zh_en_atoms.py +139 -139
- package/md_cg/signer.py +562 -562
- package/md_cg/sources.py +815 -582
- package/md_cg/statushdr.py +179 -179
- package/md_cg/stg.py +48 -37
- package/md_cg/subgraph.py +729 -729
- package/md_cg/sustain.py +1138 -1138
- package/md_cg/tasks.py +470 -470
- package/md_cg/test_action_derive.py +203 -203
- package/md_cg/test_audit_rotate.py +270 -270
- package/md_cg/test_autonomy.py +143 -143
- package/md_cg/test_bench_governance.py +102 -102
- package/md_cg/test_blindspot_tickets.py +166 -166
- package/md_cg/test_branches.py +249 -249
- package/md_cg/test_ccg_perturb.py +184 -184
- package/md_cg/test_ccgc.py +433 -433
- package/md_cg/test_census_prune.py +81 -81
- package/md_cg/test_cond_compose_anchors.py +76 -76
- package/md_cg/test_cond_match.py +165 -165
- package/md_cg/test_condition_anchor.py +81 -81
- package/md_cg/test_d_meta.py +412 -412
- package/md_cg/test_datapath_root.py +199 -199
- package/md_cg/test_en_pipeline.py +166 -166
- package/md_cg/test_gain_gate.py +212 -212
- package/md_cg/test_health_scale.py +173 -173
- package/md_cg/test_hive_ingest.py +285 -0
- package/md_cg/test_hot_cold.py +215 -215
- package/md_cg/test_hyperedge.py +245 -245
- package/md_cg/test_i26_empty_first_write.py +116 -0
- package/md_cg/test_i27_e041_identity.py +128 -0
- package/md_cg/test_i28_hotcache_prodpath.py +122 -0
- package/md_cg/test_identity_attribution.py +147 -147
- package/md_cg/test_index_durability.py +224 -224
- package/md_cg/test_interop.py +93 -0
- package/md_cg/test_lifecycle.py +309 -309
- package/md_cg/test_linkref.py +306 -306
- package/md_cg/test_lock.py +43 -43
- package/md_cg/test_md_access_parity.py +255 -255
- package/md_cg/test_md_writepath.py +345 -345
- package/md_cg/test_mdstore_search_parity.py +160 -0
- package/md_cg/test_mr_m2.py +587 -587
- package/md_cg/test_mr_m3.py +710 -710
- package/md_cg/test_mr_m4.py +485 -485
- package/md_cg/test_p0.py +250 -250
- package/md_cg/test_p1.py +316 -316
- package/md_cg/test_p10_identity.py +173 -173
- package/md_cg/test_p11_consistency.py +233 -233
- package/md_cg/test_p12_metacognition.py +212 -212
- package/md_cg/test_p13_encryption.py +241 -241
- package/md_cg/test_p14_sustain.py +249 -249
- package/md_cg/test_p15_scrub.py +280 -280
- package/md_cg/test_p16_self_state.py +301 -301
- package/md_cg/test_p17_predict.py +354 -354
- package/md_cg/test_p18_whitebox.py +171 -171
- package/md_cg/test_p19_migrate_roleplay.py +149 -149
- package/md_cg/test_p20_evolution.py +315 -315
- package/md_cg/test_p21_tokens.py +293 -270
- package/md_cg/test_p22_theory.py +175 -175
- package/md_cg/test_p23_links.py +311 -311
- package/md_cg/test_p24_evidence.py +227 -227
- package/md_cg/test_p25_weights.py +156 -156
- package/md_cg/test_p26_refindex.py +416 -416
- package/md_cg/test_p27_docindex.py +765 -765
- package/md_cg/test_p28_refcheck.py +305 -305
- package/md_cg/test_p29_session_ingest_export.py +354 -333
- package/md_cg/test_p3.py +11 -2
- package/md_cg/test_p30_maintain.py +330 -330
- package/md_cg/test_p31_insight.py +534 -534
- package/md_cg/test_p32_backfill.py +298 -298
- package/md_cg/test_p33_ccg_wiring.py +293 -293
- package/md_cg/test_p34_crosscheck.py +331 -331
- package/md_cg/test_p35_conditioned_claim.py +252 -252
- package/md_cg/test_p36_kp_align.py +230 -230
- package/md_cg/test_p37_condition_space.py +248 -248
- package/md_cg/test_p38_concurrent_flush.py +102 -0
- package/md_cg/test_p38_contextualize.py +273 -273
- package/md_cg/test_p39_verify_flow.py +113 -0
- package/md_cg/test_p39_vision_evidence.py +369 -369
- package/md_cg/test_p40_refine_worklist.py +241 -241
- package/md_cg/test_p41_evolve_patrol.py +224 -224
- package/md_cg/test_p42_provenance.py +269 -269
- package/md_cg/test_p43_pooling.py +412 -398
- package/md_cg/test_p44_md_whitebox.py +231 -231
- package/md_cg/test_p45_session_identity.py +219 -219
- package/md_cg/test_p46_unit_scope.py +272 -272
- package/md_cg/test_p47_session_view.py +281 -0
- package/md_cg/test_p4_fuzzy.py +223 -223
- package/md_cg/test_p5_semantic.py +226 -226
- package/md_cg/test_p6_consolidate.py +440 -387
- package/md_cg/test_p7_goals_recent.py +202 -202
- package/md_cg/test_p8_subgraph_chain.py +200 -200
- package/md_cg/test_p9_forget_protect.py +231 -231
- package/md_cg/test_predict_beta.py +135 -135
- package/md_cg/test_preflight_failclosed.py +100 -100
- package/md_cg/test_progressive.py +146 -146
- package/md_cg/test_protocol.py +243 -243
- package/md_cg/test_reach.py +378 -378
- package/md_cg/test_reach_keys.py +201 -201
- package/md_cg/test_read_clip.py +141 -141
- package/md_cg/test_readcache_prodpath.py +155 -0
- package/md_cg/test_retr_gates_prodpath.py +140 -0
- package/md_cg/test_retr_s1.py +340 -340
- package/md_cg/test_retr_s1b.py +209 -209
- package/md_cg/test_retr_s3.py +194 -194
- package/md_cg/test_retr_s4.py +163 -163
- package/md_cg/test_retr_s5.py +200 -200
- package/md_cg/test_retr_s6.py +157 -157
- package/md_cg/test_retr_s7.py +384 -384
- package/md_cg/test_retr_s8_time.py +369 -316
- package/md_cg/test_retr_s9_edges.py +286 -286
- package/md_cg/test_retr_s9_entity_ctx.py +175 -175
- package/md_cg/test_review_conformance.py +367 -367
- package/md_cg/test_role_views.py +354 -354
- package/md_cg/test_sem_noise.py +242 -242
- package/md_cg/test_semantic_canonical.py +241 -241
- package/md_cg/test_subproc_encoding.py +192 -192
- package/md_cg/test_sustain_mutual.py +153 -153
- package/md_cg/test_tasks.py +409 -409
- package/md_cg/test_tool_face.py +189 -189
- package/md_cg/test_transfer.py +180 -180
- package/md_cg/test_trust.py +361 -361
- package/md_cg/test_twophase.py +286 -286
- package/md_cg/test_v14_fixes.py +397 -397
- package/md_cg/test_validity_filter.py +280 -280
- package/md_cg/test_verify_answer.py +138 -138
- package/md_cg/test_wisdom_md_store.py +292 -292
- package/md_cg/test_writelimit.py +197 -197
- package/md_cg/test_writepipe.py +214 -214
- package/md_cg/theory.py +273 -273
- package/md_cg/tokens.py +677 -663
- package/md_cg/tool_face.py +260 -260
- package/md_cg/trust.py +986 -950
- package/md_cg/twophase.py +231 -231
- package/md_cg/units.py +667 -667
- package/md_cg/vision_evidence.py +666 -666
- package/md_cg/weights.py +624 -624
- package/md_cg/whitebox.py +527 -527
- package/md_cg/whitebox_kb/__init__.py +37 -37
- package/md_cg/whitebox_kb/aeis_core/__init__.py +42 -42
- package/md_cg/whitebox_kb/aeis_core/semantic.py +280 -280
- package/md_cg/whitebox_kb/aeis_core/textutil.py +13 -13
- package/md_cg/whitebox_kb/engine.py +310 -310
- package/md_cg/whitebox_kb/seed_knowledge//346/231/272/350/203/275/350/256/2723.4.md +5260 -5260
- package/md_cg/whitebox_kb/wisdom/browser_units.py +2631 -2631
- package/md_cg/whitebox_kb/wisdom/causal_discover.py +432 -432
- package/md_cg/whitebox_kb/wisdom/chat_engine.py +1506 -1506
- package/md_cg/whitebox_kb/wisdom/code_solidified.json +6195 -6195
- package/md_cg/whitebox_kb/wisdom/compiler_code_units.py +3033 -3033
- package/md_cg/whitebox_kb/wisdom/condition_algebra.py +112 -112
- package/md_cg/whitebox_kb/wisdom/condition_frame.py +315 -315
- package/md_cg/whitebox_kb/wisdom/condition_kb.py +108 -108
- package/md_cg/whitebox_kb/wisdom/conflict_map.json +4445 -4445
- package/md_cg/whitebox_kb/wisdom/core/lexer.py +512 -512
- package/md_cg/whitebox_kb/wisdom/core/name_checker.py +1023 -1023
- package/md_cg/whitebox_kb/wisdom/cspmn.py +258 -258
- package/md_cg/whitebox_kb/wisdom/csre.py +264 -264
- package/md_cg/whitebox_kb/wisdom/danmaku_audit.py +252 -252
- package/md_cg/whitebox_kb/wisdom/distilled_condition_units.json +6417 -6417
- package/md_cg/whitebox_kb/wisdom/docs/WB-EVAL-20260902b.json +1950 -1950
- package/md_cg/whitebox_kb/wisdom/docs/WB-EVAL-20260902c.json +1296 -1296
- package/md_cg/whitebox_kb/wisdom/docs/whitebox_capability_graph_demo.json +59 -59
- package/md_cg/whitebox_kb/wisdom/graph_db_units.py +3089 -3089
- package/md_cg/whitebox_kb/wisdom/knowledge_points.py +318 -318
- package/md_cg/whitebox_kb/wisdom/md_access.py +470 -470
- package/md_cg/whitebox_kb/wisdom/md_store.py +276 -251
- package/md_cg/whitebox_kb/wisdom/migrate_wisdom.py +476 -476
- package/md_cg/whitebox_kb/wisdom/navigate.py +248 -248
- package/md_cg/whitebox_kb/wisdom/neural_retrieve.py +224 -224
- package/md_cg/whitebox_kb/wisdom/os_units.py +2735 -2735
- package/md_cg/whitebox_kb/wisdom/pattern_separation.py +376 -376
- package/md_cg/whitebox_kb/wisdom/prereq_map.json +364 -364
- package/md_cg/whitebox_kb/wisdom/python_code_units.py +2766 -2766
- package/md_cg/whitebox_kb/wisdom/role_solidified.json +7 -7
- package/md_cg/whitebox_kb/wisdom/route_memory.py +244 -244
- package/md_cg/whitebox_kb/wisdom/scene_reconstruction.py +148 -148
- package/md_cg/whitebox_kb/wisdom/snr_report.json +40 -40
- package/md_cg/whitebox_kb/wisdom/test_code_compose_domains.py +7541 -7541
- package/md_cg/whitebox_kb/wisdom/test_compiler_self_bootstrap.py +354 -354
- package/md_cg/whitebox_kb/wisdom/test_ecosystem_assembly.py +158 -158
- package/md_cg/whitebox_kb/wisdom/test_ecosystem_demos.py +193 -193
- package/md_cg/whitebox_kb/wisdom/test_graph_db.py +292 -292
- package/md_cg/whitebox_kb/wisdom/test_python_self_bootstrap.py +160 -160
- package/md_cg/whitebox_kb/wisdom/trigger_words_index.json +4366 -4366
- package/md_cg/whitebox_kb/wisdom/verifier.py +1297 -1297
- package/md_cg/writelimit.py +356 -356
- package/md_cg/writepipe.py +550 -542
- package/package.json +97 -96
- package/skills/plugin.json +54 -54
- package/skills/skills/designer-perspective/SKILL.md +158 -158
- package/skills/skills/designer-perspective/references/01-observation-position.md +66 -66
- package/skills/skills/designer-perspective/references/02-structure-recognition.md +62 -62
- package/skills/skills/designer-perspective/references/03-direction-judgment.md +55 -55
- package/skills/skills/designer-perspective/references/04-qualification-verdict.md +72 -72
- package/skills/skills/designer-perspective/references/05-condition-attribution.md +74 -74
- package/skills/skills/designer-perspective/scripts/designer.py +545 -545
- package/skills/skills/designer-perspective/tests/cases.jsonl +17 -17
- package/skills/skills/designer-perspective/tests/selftest.py +61 -61
- package/skills/skills/lingshu-browser/SKILL.md +60 -60
- package/skills/skills/lingshu-compiler/SKILL.md +56 -56
- package/skills/skills/lingshu-compiler/units/analyze-type-infer/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/check-name-real/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compile-assign/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compile-expr-tree/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compile-full-pipeline/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compile-func-def/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compile-if-then/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compile-logic-expr/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compile-recursive/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compile-scope/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compile-type-check/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compile-while/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-0010c4bf/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-0355bffb/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-0361708a/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-054a0414/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-05a1691a/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-05eeed1e/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-0622a1f6/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-08b54217/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-0a62b70c/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-0ab24d00/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-0e093688/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-0e82b966/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-0ee9b9b9/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-0f3787e6/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-1028685f/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-11897630/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-16661b9b/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-1f722303/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-25be1262/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-2a76ba07/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-2dbea54a/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-2df52f16/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-2ec2c9d2/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-2f8c8f39/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-38378ac7/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-39457d2e/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-39fb5926/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-47f4fbfa/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-4a8cd1f1/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-4b230b6b/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-4cbbda95/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-4d5a68ff/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-56dc9bdd/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-57e76ebe/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-61ff016b/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-63eae588/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-64c4224b/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-66377955/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-674ab4f6/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-6af76fd6/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-6d979db2/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-6de326c0/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-6f1c0eea/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-724d6c9b/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-7690177f/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-7b229a7d/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-7f471b3a/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-815cad08/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-83c61634/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-8c798c81/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-8dd747ac/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-90324d0a/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-94b8d72d/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-94f12231/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-95937c16/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-98a5625b/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-98b4c42f/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-98e3894a/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-9bdfe4b8/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-9d9b4e83/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-9f7be5ad/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-a6daf076/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-a7995a0c/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-a8399248/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-aabbd099/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-afe169d8/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-b0678bda/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-b09bd196/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-b1396e23/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-b9b31ce0/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-c10264a7/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-cb1e8e4b/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-ccafd438/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-cda9c262/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-ce648068/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-cf5776a4/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-d974e5d3/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-e3979fd3/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-eb1cf2b5/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-ecb30d5b/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-f8c8b24b/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-f99fedbe/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-fa8ff5f7/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/compiler-fe1b058d/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/lex-chinese-program/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/lex-dao-de-jing/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/lex-nine-chapters/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-arithmetic/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-array-ops/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-closure-call/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-closure-create/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-compare/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-cond-jump/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-cond-space/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-exception/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-func-call/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-loop-run/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-profiling/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-refcount/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-run-loop/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-short-circuit/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-stack-guard/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-stack-ops/SKILL.md +45 -45
- package/skills/skills/lingshu-compiler/units/vm-trust-accum/SKILL.md +45 -45
- package/skills/skills/lingshu-graph/SKILL.md +63 -63
- package/skills/skills/lingshu-net/SKILL.md +48 -48
- package/skills/skills/lingshu-os/SKILL.md +64 -64
- package/skills/skills/lingshu-pylang/SKILL.md +71 -71
- package/src/bridge.ts +401 -401
- package/src/hooks.ts +38 -2
- package/src/lib/datapath.ts +326 -326
- package/src/lib/mdcg_client.ts +413 -413
- package/src/lib/mutual.ts +428 -428
- package/src/lib/prompt_safety.ts +62 -62
- package/src/lib/python_path.ts +71 -71
- package/src/lib/roleplay_web.ts +932 -932
- package/src/lib/token_store.ts +192 -192
- package/src/tools.ts +212 -212
- package/zcode/AGENTS.md +11 -3
- package/zcode/README.md +41 -41
- /package/docs/{mdcg → hive}//344/270/273/344/273/243/347/220/206/345/255/220/344/273/243/347/220/206/350/256/260/345/277/206/346/236/266/346/236/204/350/256/276/350/256/241.md" +0 -0
|
@@ -1,512 +1,512 @@
|
|
|
1
|
-
"""
|
|
2
|
-
lexer.py · 词法分析器 v2.0(生产版)
|
|
3
|
-
中文分词 + Token 识别
|
|
4
|
-
支持道德经助记符、九章算术结构、中文标点
|
|
5
|
-
|
|
6
|
-
v2.0 算法(两阶段):
|
|
7
|
-
阶段一(粗分):逐字符扫描,按"类型"分组
|
|
8
|
-
- 中文串(连续 CJK)
|
|
9
|
-
- 字母串(连续 ASCII 字母/数字/下划线)
|
|
10
|
-
- 数字串(连续数字,含小数点)
|
|
11
|
-
- 标点(单个)
|
|
12
|
-
- 空白(跳过)
|
|
13
|
-
- 字符串(引号包裹)
|
|
14
|
-
|
|
15
|
-
阶段二(精分):对每个中文串/字母串做关键字切分
|
|
16
|
-
- 使用正向最大匹配
|
|
17
|
-
- 关键字 → Token
|
|
18
|
-
- 非关键字 → IDENTIFIER
|
|
19
|
-
"""
|
|
20
|
-
|
|
21
|
-
from enum import Enum, auto
|
|
22
|
-
from dataclasses import dataclass
|
|
23
|
-
from typing import List, Tuple
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
# =============================================================================
|
|
27
|
-
# Token 类型定义
|
|
28
|
-
# =============================================================================
|
|
29
|
-
|
|
30
|
-
class TokenType(Enum):
|
|
31
|
-
"""Token 类型枚举"""
|
|
32
|
-
|
|
33
|
-
# === 道德经助记符(指令集) ===
|
|
34
|
-
DAO = auto() # 道
|
|
35
|
-
DE = auto() # 德
|
|
36
|
-
ZIRAN = auto() # 自然
|
|
37
|
-
WUWEI = auto() # 无为
|
|
38
|
-
GU = auto() # 谷
|
|
39
|
-
PIN = auto() # 牝
|
|
40
|
-
ROU = auto() # 柔
|
|
41
|
-
PU = auto() # 朴
|
|
42
|
-
ZHI = auto() # 止
|
|
43
|
-
ZHIZU = auto() # 知足
|
|
44
|
-
|
|
45
|
-
# === 九章算术结构关键字 ===
|
|
46
|
-
WENYUE = auto() # 问曰
|
|
47
|
-
DAYUE = auto() # 答曰
|
|
48
|
-
SHUYUE = auto() # 术曰
|
|
49
|
-
|
|
50
|
-
# === 条件/逻辑关键字 ===
|
|
51
|
-
RUO = auto() # 若
|
|
52
|
-
ZE = auto() # 则
|
|
53
|
-
FOUZE = auto() # 否则
|
|
54
|
-
YU = auto() # 于
|
|
55
|
-
WEI = auto() # 为
|
|
56
|
-
BUWEI = auto() # 不为
|
|
57
|
-
QIE = auto() # 且
|
|
58
|
-
HUO = auto() # 或
|
|
59
|
-
FEI = auto() # 非
|
|
60
|
-
DENGYU = auto() # 等于
|
|
61
|
-
DAYU = auto() # 大于
|
|
62
|
-
XIAOYU = auto() # 小于
|
|
63
|
-
|
|
64
|
-
# === 循环关键字(当…执行:白箱循环语法)===
|
|
65
|
-
DANG = auto() # 当
|
|
66
|
-
ZHIXING = auto() # 执行
|
|
67
|
-
|
|
68
|
-
# === 函数关键字(定义…返回:函数抽象)===
|
|
69
|
-
DINGYI = auto() # 定义
|
|
70
|
-
FANHUI = auto() # 返回
|
|
71
|
-
|
|
72
|
-
# === 标识符与常量 ===
|
|
73
|
-
IDENTIFIER = auto() # 标识符
|
|
74
|
-
NUMBER = auto() # 数值常量
|
|
75
|
-
STRING = auto() # 字符串常量
|
|
76
|
-
|
|
77
|
-
# === 标点符号 ===
|
|
78
|
-
COMMA = auto() # ,
|
|
79
|
-
PERIOD = auto() # 。
|
|
80
|
-
SEMICOLON = auto() # ;
|
|
81
|
-
COLON = auto() # :
|
|
82
|
-
LPAREN = auto() # (
|
|
83
|
-
RPAREN = auto() # )
|
|
84
|
-
ARROW = auto() # →
|
|
85
|
-
QUESTION = auto() # ?
|
|
86
|
-
EXCLAM = auto() # !
|
|
87
|
-
EQUALS = auto() # = 或 =(赋值符号)
|
|
88
|
-
|
|
89
|
-
# === 算术运算符(循环体/表达式需要)===
|
|
90
|
-
OP_ADD = auto() # +
|
|
91
|
-
OP_SUB = auto() # -
|
|
92
|
-
OP_MUL = auto() # *
|
|
93
|
-
OP_DIV = auto() # /
|
|
94
|
-
|
|
95
|
-
# === 特殊 ===
|
|
96
|
-
COMMENT = auto() # 注释
|
|
97
|
-
NEWLINE = auto() # 换行
|
|
98
|
-
EOF = auto() # 文件结束
|
|
99
|
-
UNKNOWN = auto() # 未知
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
# =============================================================================
|
|
103
|
-
# Token 数据结构
|
|
104
|
-
# =============================================================================
|
|
105
|
-
|
|
106
|
-
@dataclass
|
|
107
|
-
class Token:
|
|
108
|
-
"""Token 数据类"""
|
|
109
|
-
type: TokenType
|
|
110
|
-
value: str
|
|
111
|
-
line: int = 1
|
|
112
|
-
column: int = 1
|
|
113
|
-
|
|
114
|
-
def __repr__(self) -> str:
|
|
115
|
-
"""Token 调试表示:类型·值·位置一行式。"""
|
|
116
|
-
v = str(self.value)[:30]
|
|
117
|
-
if len(str(self.value)) > 30:
|
|
118
|
-
v += "..."
|
|
119
|
-
return f"Token({self.type.name}, '{v}', L{self.line}:C{self.column})"
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
# =============================================================================
|
|
123
|
-
# 关键字映射表
|
|
124
|
-
# =============================================================================
|
|
125
|
-
|
|
126
|
-
# 所有关键字集合
|
|
127
|
-
KEYWORDS = {
|
|
128
|
-
# 道德经
|
|
129
|
-
"道", "德", "自然", "无为", "谷", "牝", "柔", "朴", "止", "知足",
|
|
130
|
-
# 九章算术
|
|
131
|
-
"问曰", "答曰", "术曰",
|
|
132
|
-
# 条件/逻辑
|
|
133
|
-
"若", "则", "否则", "于", "为", "不为", "且", "或", "非",
|
|
134
|
-
"等于", "大于", "小于",
|
|
135
|
-
# 循环(当…执行:白箱循环语法)
|
|
136
|
-
"当", "执行",
|
|
137
|
-
# 函数(定义…返回:函数抽象)
|
|
138
|
-
"定义", "返回",
|
|
139
|
-
# 中文算术词(加/减/乘/除 → 运算符)
|
|
140
|
-
"加", "减", "乘", "除",
|
|
141
|
-
}
|
|
142
|
-
|
|
143
|
-
# 关键字 → TokenType
|
|
144
|
-
KEYWORD_MAP = {
|
|
145
|
-
"道": TokenType.DAO,
|
|
146
|
-
"德": TokenType.DE,
|
|
147
|
-
"自然": TokenType.ZIRAN,
|
|
148
|
-
"无为": TokenType.WUWEI,
|
|
149
|
-
"谷": TokenType.GU,
|
|
150
|
-
"牝": TokenType.PIN,
|
|
151
|
-
"柔": TokenType.ROU,
|
|
152
|
-
"朴": TokenType.PU,
|
|
153
|
-
"止": TokenType.ZHI,
|
|
154
|
-
"知足": TokenType.ZHIZU,
|
|
155
|
-
"问曰": TokenType.WENYUE,
|
|
156
|
-
"答曰": TokenType.DAYUE,
|
|
157
|
-
"术曰": TokenType.SHUYUE,
|
|
158
|
-
"若": TokenType.RUO,
|
|
159
|
-
"则": TokenType.ZE,
|
|
160
|
-
"否则": TokenType.FOUZE,
|
|
161
|
-
"于": TokenType.YU,
|
|
162
|
-
"为": TokenType.WEI,
|
|
163
|
-
"不为": TokenType.BUWEI,
|
|
164
|
-
"且": TokenType.QIE,
|
|
165
|
-
"或": TokenType.HUO,
|
|
166
|
-
"非": TokenType.FEI,
|
|
167
|
-
"等于": TokenType.DENGYU,
|
|
168
|
-
"大于": TokenType.DAYU,
|
|
169
|
-
"小于": TokenType.XIAOYU,
|
|
170
|
-
"当": TokenType.DANG,
|
|
171
|
-
"执行": TokenType.ZHIXING,
|
|
172
|
-
"定义": TokenType.DINGYI,
|
|
173
|
-
"返回": TokenType.FANHUI,
|
|
174
|
-
"加": TokenType.OP_ADD,
|
|
175
|
-
"减": TokenType.OP_SUB,
|
|
176
|
-
"乘": TokenType.OP_MUL,
|
|
177
|
-
"除": TokenType.OP_DIV,
|
|
178
|
-
}
|
|
179
|
-
|
|
180
|
-
# 按长度降序排列
|
|
181
|
-
SORTED_KW = sorted(KEYWORDS, key=len, reverse=True)
|
|
182
|
-
|
|
183
|
-
# 中文标点映射
|
|
184
|
-
PUNCTUATION_MAP = {
|
|
185
|
-
",": TokenType.COMMA, ",": TokenType.COMMA,
|
|
186
|
-
"。": TokenType.PERIOD, ".": TokenType.PERIOD,
|
|
187
|
-
";": TokenType.SEMICOLON, ";": TokenType.SEMICOLON,
|
|
188
|
-
":": TokenType.COLON, ":": TokenType.COLON,
|
|
189
|
-
"(": TokenType.LPAREN, "(": TokenType.LPAREN,
|
|
190
|
-
")": TokenType.RPAREN, ")": TokenType.RPAREN,
|
|
191
|
-
"→": TokenType.ARROW,
|
|
192
|
-
"?": TokenType.QUESTION, "?": TokenType.QUESTION,
|
|
193
|
-
"!": TokenType.EXCLAM, "!": TokenType.EXCLAM,
|
|
194
|
-
"=": TokenType.EQUALS, "=": TokenType.EQUALS,
|
|
195
|
-
"+": TokenType.OP_ADD, "+": TokenType.OP_ADD,
|
|
196
|
-
"-": TokenType.OP_SUB, "-": TokenType.OP_SUB,
|
|
197
|
-
"*": TokenType.OP_MUL, "×": TokenType.OP_MUL,
|
|
198
|
-
"/": TokenType.OP_DIV, "÷": TokenType.OP_DIV,
|
|
199
|
-
}
|
|
200
|
-
|
|
201
|
-
|
|
202
|
-
# =============================================================================
|
|
203
|
-
# 工具函数
|
|
204
|
-
# =============================================================================
|
|
205
|
-
|
|
206
|
-
def _is_cjk(ch: str) -> bool:
|
|
207
|
-
"""是否为 CJK 统一汉字"""
|
|
208
|
-
code = ord(ch)
|
|
209
|
-
return 0x4E00 <= code <= 0x9FFF
|
|
210
|
-
|
|
211
|
-
def _is_cjk_or_alpha(ch: str) -> bool:
|
|
212
|
-
"""是否为中文、字母、下划线"""
|
|
213
|
-
return _is_cjk(ch) or ch.isalpha() or ch == "_"
|
|
214
|
-
|
|
215
|
-
|
|
216
|
-
# =============================================================================
|
|
217
|
-
# 词法分析器
|
|
218
|
-
# =============================================================================
|
|
219
|
-
|
|
220
|
-
class Lexer:
|
|
221
|
-
"""
|
|
222
|
-
词法分析器 v2.0
|
|
223
|
-
|
|
224
|
-
两阶段分词:
|
|
225
|
-
阶段一:粗分(按字符类型分组)
|
|
226
|
-
阶段二:精分(对中文/字母串做关键字切分)
|
|
227
|
-
"""
|
|
228
|
-
|
|
229
|
-
def __init__(self, source: str):
|
|
230
|
-
"""Token 构造:类型·字面值·行号列号。"""
|
|
231
|
-
self.source = source
|
|
232
|
-
self.pos = 0
|
|
233
|
-
self.line = 1
|
|
234
|
-
self.column = 1
|
|
235
|
-
self.tokens: List[Token] = []
|
|
236
|
-
self.errors: List[str] = []
|
|
237
|
-
|
|
238
|
-
def tokenize(self) -> Tuple[List[Token], List[str]]:
|
|
239
|
-
"""执行词法分析"""
|
|
240
|
-
self.tokens = []
|
|
241
|
-
self.errors = []
|
|
242
|
-
self.pos = 0
|
|
243
|
-
self.line = 1
|
|
244
|
-
self.column = 1
|
|
245
|
-
|
|
246
|
-
while self.pos < len(self.source):
|
|
247
|
-
ch = self.source[self.pos]
|
|
248
|
-
|
|
249
|
-
# 换行
|
|
250
|
-
if ch == "\n":
|
|
251
|
-
self.line += 1
|
|
252
|
-
self.column = 1
|
|
253
|
-
self.pos += 1
|
|
254
|
-
continue
|
|
255
|
-
|
|
256
|
-
# 空白
|
|
257
|
-
if ch in (" ", "\t", "\r"):
|
|
258
|
-
self.column += 1
|
|
259
|
-
self.pos += 1
|
|
260
|
-
continue
|
|
261
|
-
|
|
262
|
-
# 注释 //
|
|
263
|
-
if ch == "/" and self.pos + 1 < len(self.source) and self.source[self.pos + 1] == "/":
|
|
264
|
-
self._skip_comment()
|
|
265
|
-
continue
|
|
266
|
-
|
|
267
|
-
# 字符串
|
|
268
|
-
if ch == '"' or ch == "\u201c":
|
|
269
|
-
self._read_string()
|
|
270
|
-
continue
|
|
271
|
-
|
|
272
|
-
# 数字(包括 . 开头的小数)
|
|
273
|
-
if ch.isdigit() or ch == "." or (ch == "-" and self._peek_isdigit()):
|
|
274
|
-
self._read_number()
|
|
275
|
-
continue
|
|
276
|
-
|
|
277
|
-
# 中文标点
|
|
278
|
-
if ch in PUNCTUATION_MAP:
|
|
279
|
-
self._emit(PUNCTUATION_MAP[ch], ch)
|
|
280
|
-
self.pos += 1
|
|
281
|
-
self.column += 1
|
|
282
|
-
continue
|
|
283
|
-
|
|
284
|
-
# 赋值符号 = (ASCII)或 =(全角)
|
|
285
|
-
if ch == "=" or ch == "\uFF1D":
|
|
286
|
-
self._emit(TokenType.EQUALS, ch)
|
|
287
|
-
self.pos += 1
|
|
288
|
-
self.column += 1
|
|
289
|
-
continue
|
|
290
|
-
|
|
291
|
-
# 中文/字母/下划线 → 粗分 + 精分
|
|
292
|
-
if _is_cjk_or_alpha(ch):
|
|
293
|
-
self._read_and_segment()
|
|
294
|
-
continue
|
|
295
|
-
|
|
296
|
-
# 未知字符
|
|
297
|
-
self.errors.append(f"L{self.line}:C{self.column} 未知字符: '{ch}' (U+{ord(ch):04X})")
|
|
298
|
-
self.pos += 1
|
|
299
|
-
self.column += 1
|
|
300
|
-
|
|
301
|
-
self._emit(TokenType.EOF, "")
|
|
302
|
-
return self.tokens, self.errors
|
|
303
|
-
|
|
304
|
-
# ---- 阶段一:粗分 ----
|
|
305
|
-
|
|
306
|
-
def _read_and_segment(self):
|
|
307
|
-
"""
|
|
308
|
-
读取连续的中文/字母/数字/下划线,然后做关键字精分
|
|
309
|
-
|
|
310
|
-
这是核心方法:
|
|
311
|
-
1. 贪婪读取所有"词字符"(中文/字母/数字/下划线)
|
|
312
|
-
2. 对结果做正向最大匹配切分
|
|
313
|
-
"""
|
|
314
|
-
start_col = self.column
|
|
315
|
-
start_pos = self.pos
|
|
316
|
-
|
|
317
|
-
# 贪婪读取
|
|
318
|
-
while self.pos < len(self.source):
|
|
319
|
-
ch = self.source[self.pos]
|
|
320
|
-
if _is_cjk_or_alpha(ch) or ch.isdigit():
|
|
321
|
-
self.pos += 1
|
|
322
|
-
else:
|
|
323
|
-
break
|
|
324
|
-
|
|
325
|
-
text = self.source[start_pos:self.pos]
|
|
326
|
-
self.column += (self.pos - start_pos)
|
|
327
|
-
|
|
328
|
-
# 阶段二:精分
|
|
329
|
-
self._segment(text, start_col)
|
|
330
|
-
|
|
331
|
-
# ---- 阶段二:精分 ----
|
|
332
|
-
|
|
333
|
-
def _segment(self, text: str, start_col: int):
|
|
334
|
-
"""
|
|
335
|
-
正向最大匹配(Forward Maximum Matching)
|
|
336
|
-
|
|
337
|
-
对 text 中的每个位置,找最长的匹配关键字。
|
|
338
|
-
如果找不到关键字,发出单个字符作为 IDENTIFIER。
|
|
339
|
-
|
|
340
|
-
关键改进:使用位置指针 i 遍历 text,
|
|
341
|
-
每次从 i 开始找最长关键字。
|
|
342
|
-
找到后 i 跳过该关键字长度。
|
|
343
|
-
找不到时 i 前进 1(发出单个字符)。
|
|
344
|
-
|
|
345
|
-
标识符规则:连续 CJK 串优先整体为标识符(如「阶乘」含关键词「乘」,
|
|
346
|
-
但整体不是关键词 → 保持为标识符,避免误切分)。
|
|
347
|
-
"""
|
|
348
|
-
i = 0
|
|
349
|
-
col = start_col
|
|
350
|
-
|
|
351
|
-
while i < len(text):
|
|
352
|
-
# 尝试从位置 i 找最长关键字
|
|
353
|
-
matched_kw = None
|
|
354
|
-
matched_len = 0
|
|
355
|
-
|
|
356
|
-
for kw in SORTED_KW:
|
|
357
|
-
if text.startswith(kw, i):
|
|
358
|
-
if len(kw) > matched_len:
|
|
359
|
-
matched_kw = kw
|
|
360
|
-
matched_len = len(kw)
|
|
361
|
-
|
|
362
|
-
if matched_kw is not None:
|
|
363
|
-
# 发出关键字 token
|
|
364
|
-
self._emit(KEYWORD_MAP[matched_kw], matched_kw, col)
|
|
365
|
-
i += matched_len
|
|
366
|
-
col += matched_len
|
|
367
|
-
else:
|
|
368
|
-
# 不是关键字 → 收集连续的非关键字字符作为标识符
|
|
369
|
-
# 中文规则:连续 CJK 串优先整体为标识符(如「阶乘」含关键词「乘」,
|
|
370
|
-
# 但整串「阶乘」非关键词 → 保持整体,避免误切分)
|
|
371
|
-
ident_start = i
|
|
372
|
-
ident_col = col
|
|
373
|
-
|
|
374
|
-
if _is_cjk(text[i]):
|
|
375
|
-
while i < len(text) and _is_cjk(text[i]):
|
|
376
|
-
i += 1
|
|
377
|
-
col += 1
|
|
378
|
-
else:
|
|
379
|
-
while i < len(text):
|
|
380
|
-
ch = text[i]
|
|
381
|
-
has_kw_ahead = any(text.startswith(kw, i) for kw in SORTED_KW)
|
|
382
|
-
if has_kw_ahead:
|
|
383
|
-
break
|
|
384
|
-
i += 1
|
|
385
|
-
col += 1
|
|
386
|
-
|
|
387
|
-
ident = text[ident_start:i]
|
|
388
|
-
if ident:
|
|
389
|
-
self._emit(TokenType.IDENTIFIER, ident, ident_col)
|
|
390
|
-
|
|
391
|
-
# ---- 数字读取 ----
|
|
392
|
-
|
|
393
|
-
def _peek_isdigit(self) -> bool:
|
|
394
|
-
"""前瞻当前字符是否数字(多位数聚合判断)。"""
|
|
395
|
-
return self.pos + 1 < len(self.source) and self.source[self.pos + 1].isdigit()
|
|
396
|
-
|
|
397
|
-
def _read_number(self):
|
|
398
|
-
"""读取数值(支持整数、小数、负数)"""
|
|
399
|
-
start_col = self.column
|
|
400
|
-
result = []
|
|
401
|
-
|
|
402
|
-
# 负号
|
|
403
|
-
if self.source[self.pos] == "-":
|
|
404
|
-
result.append("-")
|
|
405
|
-
self.pos += 1
|
|
406
|
-
self.column += 1
|
|
407
|
-
|
|
408
|
-
# 整数部分
|
|
409
|
-
while self.pos < len(self.source) and self.source[self.pos].isdigit():
|
|
410
|
-
result.append(self.source[self.pos])
|
|
411
|
-
self.pos += 1
|
|
412
|
-
self.column += 1
|
|
413
|
-
|
|
414
|
-
# 小数部分
|
|
415
|
-
if self.pos < len(self.source) and self.source[self.pos] == ".":
|
|
416
|
-
result.append(".")
|
|
417
|
-
self.pos += 1
|
|
418
|
-
self.column += 1
|
|
419
|
-
while self.pos < len(self.source) and self.source[self.pos].isdigit():
|
|
420
|
-
result.append(self.source[self.pos])
|
|
421
|
-
self.pos += 1
|
|
422
|
-
self.column += 1
|
|
423
|
-
|
|
424
|
-
num_str = "".join(result)
|
|
425
|
-
try:
|
|
426
|
-
float(num_str)
|
|
427
|
-
self._emit(TokenType.NUMBER, num_str)
|
|
428
|
-
except ValueError:
|
|
429
|
-
self.errors.append(f"L{self.line}:C{start_col} 非法数值: '{num_str}'")
|
|
430
|
-
self._emit(TokenType.NUMBER, num_str)
|
|
431
|
-
|
|
432
|
-
# ---- 字符串读取 ----
|
|
433
|
-
|
|
434
|
-
def _read_string(self):
|
|
435
|
-
"""读取字符串"""
|
|
436
|
-
quote_char = self.source[self.pos]
|
|
437
|
-
end_quote = '"' if quote_char == '"' else "\u201d"
|
|
438
|
-
|
|
439
|
-
self.pos += 1
|
|
440
|
-
self.column += 1
|
|
441
|
-
result = []
|
|
442
|
-
|
|
443
|
-
while self.pos < len(self.source) and self.source[self.pos] != end_quote:
|
|
444
|
-
ch = self.source[self.pos]
|
|
445
|
-
if ch == "\n":
|
|
446
|
-
self.errors.append(f"L{self.line}:C{self.column} 字符串未闭合")
|
|
447
|
-
break
|
|
448
|
-
result.append(ch)
|
|
449
|
-
self.pos += 1
|
|
450
|
-
self.column += 1
|
|
451
|
-
|
|
452
|
-
if self.pos < len(self.source):
|
|
453
|
-
self.pos += 1 # 跳过结束引号
|
|
454
|
-
self.column += 1
|
|
455
|
-
|
|
456
|
-
self._emit(TokenType.STRING, "".join(result))
|
|
457
|
-
|
|
458
|
-
# ---- 注释跳过 ----
|
|
459
|
-
|
|
460
|
-
def _skip_comment(self):
|
|
461
|
-
"""跳过注释至本行结束。"""
|
|
462
|
-
while self.pos < len(self.source) and self.source[self.pos] != "\n":
|
|
463
|
-
self.pos += 1
|
|
464
|
-
|
|
465
|
-
# ---- Token 输出 ----
|
|
466
|
-
|
|
467
|
-
def _emit(self, token_type: TokenType, value: str, col: int = None):
|
|
468
|
-
"""输出一个 Token"""
|
|
469
|
-
c = col if col is not None else self.column
|
|
470
|
-
self.tokens.append(Token(token_type, value, self.line, c))
|
|
471
|
-
|
|
472
|
-
|
|
473
|
-
# =============================================================================
|
|
474
|
-
# 便捷函数
|
|
475
|
-
# =============================================================================
|
|
476
|
-
|
|
477
|
-
def tokenize(source: str) -> Tuple[List[Token], List[str]]:
|
|
478
|
-
"""便捷函数"""
|
|
479
|
-
lexer = Lexer(source)
|
|
480
|
-
return lexer.tokenize()
|
|
481
|
-
|
|
482
|
-
|
|
483
|
-
# =============================================================================
|
|
484
|
-
# 测试
|
|
485
|
-
# =============================================================================
|
|
486
|
-
|
|
487
|
-
if __name__ == "__main__":
|
|
488
|
-
test_code = """若条件空间为伴侣,则止情感权重于0.15。
|
|
489
|
-
道 新信任路径
|
|
490
|
-
问曰:如何验证信任?
|
|
491
|
-
答曰:信任值大于0.7。
|
|
492
|
-
术曰:1。德 累积信任值;2。自然 恢复默认。"""
|
|
493
|
-
|
|
494
|
-
print("=" * 60)
|
|
495
|
-
print("词法分析器 v2.0 测试")
|
|
496
|
-
print("=" * 60)
|
|
497
|
-
print(f"源代码:\n{test_code}\n")
|
|
498
|
-
|
|
499
|
-
tokens, errors = tokenize(test_code)
|
|
500
|
-
|
|
501
|
-
print("Token 序列:")
|
|
502
|
-
for t in tokens:
|
|
503
|
-
if t.type != TokenType.EOF:
|
|
504
|
-
print(f" {t}")
|
|
505
|
-
|
|
506
|
-
if errors:
|
|
507
|
-
print(f"\n错误:")
|
|
508
|
-
for e in errors:
|
|
509
|
-
print(f" ❌ {e}")
|
|
510
|
-
|
|
511
|
-
valid = len([t for t in tokens if t.type != TokenType.EOF])
|
|
512
|
-
print(f"\n总计:{valid} 个 Token,{len(errors)} 个错误")
|
|
1
|
+
"""
|
|
2
|
+
lexer.py · 词法分析器 v2.0(生产版)
|
|
3
|
+
中文分词 + Token 识别
|
|
4
|
+
支持道德经助记符、九章算术结构、中文标点
|
|
5
|
+
|
|
6
|
+
v2.0 算法(两阶段):
|
|
7
|
+
阶段一(粗分):逐字符扫描,按"类型"分组
|
|
8
|
+
- 中文串(连续 CJK)
|
|
9
|
+
- 字母串(连续 ASCII 字母/数字/下划线)
|
|
10
|
+
- 数字串(连续数字,含小数点)
|
|
11
|
+
- 标点(单个)
|
|
12
|
+
- 空白(跳过)
|
|
13
|
+
- 字符串(引号包裹)
|
|
14
|
+
|
|
15
|
+
阶段二(精分):对每个中文串/字母串做关键字切分
|
|
16
|
+
- 使用正向最大匹配
|
|
17
|
+
- 关键字 → Token
|
|
18
|
+
- 非关键字 → IDENTIFIER
|
|
19
|
+
"""
|
|
20
|
+
|
|
21
|
+
from enum import Enum, auto
|
|
22
|
+
from dataclasses import dataclass
|
|
23
|
+
from typing import List, Tuple
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
# =============================================================================
|
|
27
|
+
# Token 类型定义
|
|
28
|
+
# =============================================================================
|
|
29
|
+
|
|
30
|
+
class TokenType(Enum):
|
|
31
|
+
"""Token 类型枚举"""
|
|
32
|
+
|
|
33
|
+
# === 道德经助记符(指令集) ===
|
|
34
|
+
DAO = auto() # 道
|
|
35
|
+
DE = auto() # 德
|
|
36
|
+
ZIRAN = auto() # 自然
|
|
37
|
+
WUWEI = auto() # 无为
|
|
38
|
+
GU = auto() # 谷
|
|
39
|
+
PIN = auto() # 牝
|
|
40
|
+
ROU = auto() # 柔
|
|
41
|
+
PU = auto() # 朴
|
|
42
|
+
ZHI = auto() # 止
|
|
43
|
+
ZHIZU = auto() # 知足
|
|
44
|
+
|
|
45
|
+
# === 九章算术结构关键字 ===
|
|
46
|
+
WENYUE = auto() # 问曰
|
|
47
|
+
DAYUE = auto() # 答曰
|
|
48
|
+
SHUYUE = auto() # 术曰
|
|
49
|
+
|
|
50
|
+
# === 条件/逻辑关键字 ===
|
|
51
|
+
RUO = auto() # 若
|
|
52
|
+
ZE = auto() # 则
|
|
53
|
+
FOUZE = auto() # 否则
|
|
54
|
+
YU = auto() # 于
|
|
55
|
+
WEI = auto() # 为
|
|
56
|
+
BUWEI = auto() # 不为
|
|
57
|
+
QIE = auto() # 且
|
|
58
|
+
HUO = auto() # 或
|
|
59
|
+
FEI = auto() # 非
|
|
60
|
+
DENGYU = auto() # 等于
|
|
61
|
+
DAYU = auto() # 大于
|
|
62
|
+
XIAOYU = auto() # 小于
|
|
63
|
+
|
|
64
|
+
# === 循环关键字(当…执行:白箱循环语法)===
|
|
65
|
+
DANG = auto() # 当
|
|
66
|
+
ZHIXING = auto() # 执行
|
|
67
|
+
|
|
68
|
+
# === 函数关键字(定义…返回:函数抽象)===
|
|
69
|
+
DINGYI = auto() # 定义
|
|
70
|
+
FANHUI = auto() # 返回
|
|
71
|
+
|
|
72
|
+
# === 标识符与常量 ===
|
|
73
|
+
IDENTIFIER = auto() # 标识符
|
|
74
|
+
NUMBER = auto() # 数值常量
|
|
75
|
+
STRING = auto() # 字符串常量
|
|
76
|
+
|
|
77
|
+
# === 标点符号 ===
|
|
78
|
+
COMMA = auto() # ,
|
|
79
|
+
PERIOD = auto() # 。
|
|
80
|
+
SEMICOLON = auto() # ;
|
|
81
|
+
COLON = auto() # :
|
|
82
|
+
LPAREN = auto() # (
|
|
83
|
+
RPAREN = auto() # )
|
|
84
|
+
ARROW = auto() # →
|
|
85
|
+
QUESTION = auto() # ?
|
|
86
|
+
EXCLAM = auto() # !
|
|
87
|
+
EQUALS = auto() # = 或 =(赋值符号)
|
|
88
|
+
|
|
89
|
+
# === 算术运算符(循环体/表达式需要)===
|
|
90
|
+
OP_ADD = auto() # +
|
|
91
|
+
OP_SUB = auto() # -
|
|
92
|
+
OP_MUL = auto() # *
|
|
93
|
+
OP_DIV = auto() # /
|
|
94
|
+
|
|
95
|
+
# === 特殊 ===
|
|
96
|
+
COMMENT = auto() # 注释
|
|
97
|
+
NEWLINE = auto() # 换行
|
|
98
|
+
EOF = auto() # 文件结束
|
|
99
|
+
UNKNOWN = auto() # 未知
|
|
100
|
+
|
|
101
|
+
|
|
102
|
+
# =============================================================================
|
|
103
|
+
# Token 数据结构
|
|
104
|
+
# =============================================================================
|
|
105
|
+
|
|
106
|
+
@dataclass
|
|
107
|
+
class Token:
|
|
108
|
+
"""Token 数据类"""
|
|
109
|
+
type: TokenType
|
|
110
|
+
value: str
|
|
111
|
+
line: int = 1
|
|
112
|
+
column: int = 1
|
|
113
|
+
|
|
114
|
+
def __repr__(self) -> str:
|
|
115
|
+
"""Token 调试表示:类型·值·位置一行式。"""
|
|
116
|
+
v = str(self.value)[:30]
|
|
117
|
+
if len(str(self.value)) > 30:
|
|
118
|
+
v += "..."
|
|
119
|
+
return f"Token({self.type.name}, '{v}', L{self.line}:C{self.column})"
|
|
120
|
+
|
|
121
|
+
|
|
122
|
+
# =============================================================================
|
|
123
|
+
# 关键字映射表
|
|
124
|
+
# =============================================================================
|
|
125
|
+
|
|
126
|
+
# 所有关键字集合
|
|
127
|
+
KEYWORDS = {
|
|
128
|
+
# 道德经
|
|
129
|
+
"道", "德", "自然", "无为", "谷", "牝", "柔", "朴", "止", "知足",
|
|
130
|
+
# 九章算术
|
|
131
|
+
"问曰", "答曰", "术曰",
|
|
132
|
+
# 条件/逻辑
|
|
133
|
+
"若", "则", "否则", "于", "为", "不为", "且", "或", "非",
|
|
134
|
+
"等于", "大于", "小于",
|
|
135
|
+
# 循环(当…执行:白箱循环语法)
|
|
136
|
+
"当", "执行",
|
|
137
|
+
# 函数(定义…返回:函数抽象)
|
|
138
|
+
"定义", "返回",
|
|
139
|
+
# 中文算术词(加/减/乘/除 → 运算符)
|
|
140
|
+
"加", "减", "乘", "除",
|
|
141
|
+
}
|
|
142
|
+
|
|
143
|
+
# 关键字 → TokenType
|
|
144
|
+
KEYWORD_MAP = {
|
|
145
|
+
"道": TokenType.DAO,
|
|
146
|
+
"德": TokenType.DE,
|
|
147
|
+
"自然": TokenType.ZIRAN,
|
|
148
|
+
"无为": TokenType.WUWEI,
|
|
149
|
+
"谷": TokenType.GU,
|
|
150
|
+
"牝": TokenType.PIN,
|
|
151
|
+
"柔": TokenType.ROU,
|
|
152
|
+
"朴": TokenType.PU,
|
|
153
|
+
"止": TokenType.ZHI,
|
|
154
|
+
"知足": TokenType.ZHIZU,
|
|
155
|
+
"问曰": TokenType.WENYUE,
|
|
156
|
+
"答曰": TokenType.DAYUE,
|
|
157
|
+
"术曰": TokenType.SHUYUE,
|
|
158
|
+
"若": TokenType.RUO,
|
|
159
|
+
"则": TokenType.ZE,
|
|
160
|
+
"否则": TokenType.FOUZE,
|
|
161
|
+
"于": TokenType.YU,
|
|
162
|
+
"为": TokenType.WEI,
|
|
163
|
+
"不为": TokenType.BUWEI,
|
|
164
|
+
"且": TokenType.QIE,
|
|
165
|
+
"或": TokenType.HUO,
|
|
166
|
+
"非": TokenType.FEI,
|
|
167
|
+
"等于": TokenType.DENGYU,
|
|
168
|
+
"大于": TokenType.DAYU,
|
|
169
|
+
"小于": TokenType.XIAOYU,
|
|
170
|
+
"当": TokenType.DANG,
|
|
171
|
+
"执行": TokenType.ZHIXING,
|
|
172
|
+
"定义": TokenType.DINGYI,
|
|
173
|
+
"返回": TokenType.FANHUI,
|
|
174
|
+
"加": TokenType.OP_ADD,
|
|
175
|
+
"减": TokenType.OP_SUB,
|
|
176
|
+
"乘": TokenType.OP_MUL,
|
|
177
|
+
"除": TokenType.OP_DIV,
|
|
178
|
+
}
|
|
179
|
+
|
|
180
|
+
# 按长度降序排列
|
|
181
|
+
SORTED_KW = sorted(KEYWORDS, key=len, reverse=True)
|
|
182
|
+
|
|
183
|
+
# 中文标点映射
|
|
184
|
+
PUNCTUATION_MAP = {
|
|
185
|
+
",": TokenType.COMMA, ",": TokenType.COMMA,
|
|
186
|
+
"。": TokenType.PERIOD, ".": TokenType.PERIOD,
|
|
187
|
+
";": TokenType.SEMICOLON, ";": TokenType.SEMICOLON,
|
|
188
|
+
":": TokenType.COLON, ":": TokenType.COLON,
|
|
189
|
+
"(": TokenType.LPAREN, "(": TokenType.LPAREN,
|
|
190
|
+
")": TokenType.RPAREN, ")": TokenType.RPAREN,
|
|
191
|
+
"→": TokenType.ARROW,
|
|
192
|
+
"?": TokenType.QUESTION, "?": TokenType.QUESTION,
|
|
193
|
+
"!": TokenType.EXCLAM, "!": TokenType.EXCLAM,
|
|
194
|
+
"=": TokenType.EQUALS, "=": TokenType.EQUALS,
|
|
195
|
+
"+": TokenType.OP_ADD, "+": TokenType.OP_ADD,
|
|
196
|
+
"-": TokenType.OP_SUB, "-": TokenType.OP_SUB,
|
|
197
|
+
"*": TokenType.OP_MUL, "×": TokenType.OP_MUL,
|
|
198
|
+
"/": TokenType.OP_DIV, "÷": TokenType.OP_DIV,
|
|
199
|
+
}
|
|
200
|
+
|
|
201
|
+
|
|
202
|
+
# =============================================================================
|
|
203
|
+
# 工具函数
|
|
204
|
+
# =============================================================================
|
|
205
|
+
|
|
206
|
+
def _is_cjk(ch: str) -> bool:
|
|
207
|
+
"""是否为 CJK 统一汉字"""
|
|
208
|
+
code = ord(ch)
|
|
209
|
+
return 0x4E00 <= code <= 0x9FFF
|
|
210
|
+
|
|
211
|
+
def _is_cjk_or_alpha(ch: str) -> bool:
|
|
212
|
+
"""是否为中文、字母、下划线"""
|
|
213
|
+
return _is_cjk(ch) or ch.isalpha() or ch == "_"
|
|
214
|
+
|
|
215
|
+
|
|
216
|
+
# =============================================================================
|
|
217
|
+
# 词法分析器
|
|
218
|
+
# =============================================================================
|
|
219
|
+
|
|
220
|
+
class Lexer:
|
|
221
|
+
"""
|
|
222
|
+
词法分析器 v2.0
|
|
223
|
+
|
|
224
|
+
两阶段分词:
|
|
225
|
+
阶段一:粗分(按字符类型分组)
|
|
226
|
+
阶段二:精分(对中文/字母串做关键字切分)
|
|
227
|
+
"""
|
|
228
|
+
|
|
229
|
+
def __init__(self, source: str):
|
|
230
|
+
"""Token 构造:类型·字面值·行号列号。"""
|
|
231
|
+
self.source = source
|
|
232
|
+
self.pos = 0
|
|
233
|
+
self.line = 1
|
|
234
|
+
self.column = 1
|
|
235
|
+
self.tokens: List[Token] = []
|
|
236
|
+
self.errors: List[str] = []
|
|
237
|
+
|
|
238
|
+
def tokenize(self) -> Tuple[List[Token], List[str]]:
|
|
239
|
+
"""执行词法分析"""
|
|
240
|
+
self.tokens = []
|
|
241
|
+
self.errors = []
|
|
242
|
+
self.pos = 0
|
|
243
|
+
self.line = 1
|
|
244
|
+
self.column = 1
|
|
245
|
+
|
|
246
|
+
while self.pos < len(self.source):
|
|
247
|
+
ch = self.source[self.pos]
|
|
248
|
+
|
|
249
|
+
# 换行
|
|
250
|
+
if ch == "\n":
|
|
251
|
+
self.line += 1
|
|
252
|
+
self.column = 1
|
|
253
|
+
self.pos += 1
|
|
254
|
+
continue
|
|
255
|
+
|
|
256
|
+
# 空白
|
|
257
|
+
if ch in (" ", "\t", "\r"):
|
|
258
|
+
self.column += 1
|
|
259
|
+
self.pos += 1
|
|
260
|
+
continue
|
|
261
|
+
|
|
262
|
+
# 注释 //
|
|
263
|
+
if ch == "/" and self.pos + 1 < len(self.source) and self.source[self.pos + 1] == "/":
|
|
264
|
+
self._skip_comment()
|
|
265
|
+
continue
|
|
266
|
+
|
|
267
|
+
# 字符串
|
|
268
|
+
if ch == '"' or ch == "\u201c":
|
|
269
|
+
self._read_string()
|
|
270
|
+
continue
|
|
271
|
+
|
|
272
|
+
# 数字(包括 . 开头的小数)
|
|
273
|
+
if ch.isdigit() or ch == "." or (ch == "-" and self._peek_isdigit()):
|
|
274
|
+
self._read_number()
|
|
275
|
+
continue
|
|
276
|
+
|
|
277
|
+
# 中文标点
|
|
278
|
+
if ch in PUNCTUATION_MAP:
|
|
279
|
+
self._emit(PUNCTUATION_MAP[ch], ch)
|
|
280
|
+
self.pos += 1
|
|
281
|
+
self.column += 1
|
|
282
|
+
continue
|
|
283
|
+
|
|
284
|
+
# 赋值符号 = (ASCII)或 =(全角)
|
|
285
|
+
if ch == "=" or ch == "\uFF1D":
|
|
286
|
+
self._emit(TokenType.EQUALS, ch)
|
|
287
|
+
self.pos += 1
|
|
288
|
+
self.column += 1
|
|
289
|
+
continue
|
|
290
|
+
|
|
291
|
+
# 中文/字母/下划线 → 粗分 + 精分
|
|
292
|
+
if _is_cjk_or_alpha(ch):
|
|
293
|
+
self._read_and_segment()
|
|
294
|
+
continue
|
|
295
|
+
|
|
296
|
+
# 未知字符
|
|
297
|
+
self.errors.append(f"L{self.line}:C{self.column} 未知字符: '{ch}' (U+{ord(ch):04X})")
|
|
298
|
+
self.pos += 1
|
|
299
|
+
self.column += 1
|
|
300
|
+
|
|
301
|
+
self._emit(TokenType.EOF, "")
|
|
302
|
+
return self.tokens, self.errors
|
|
303
|
+
|
|
304
|
+
# ---- 阶段一:粗分 ----
|
|
305
|
+
|
|
306
|
+
def _read_and_segment(self):
|
|
307
|
+
"""
|
|
308
|
+
读取连续的中文/字母/数字/下划线,然后做关键字精分
|
|
309
|
+
|
|
310
|
+
这是核心方法:
|
|
311
|
+
1. 贪婪读取所有"词字符"(中文/字母/数字/下划线)
|
|
312
|
+
2. 对结果做正向最大匹配切分
|
|
313
|
+
"""
|
|
314
|
+
start_col = self.column
|
|
315
|
+
start_pos = self.pos
|
|
316
|
+
|
|
317
|
+
# 贪婪读取
|
|
318
|
+
while self.pos < len(self.source):
|
|
319
|
+
ch = self.source[self.pos]
|
|
320
|
+
if _is_cjk_or_alpha(ch) or ch.isdigit():
|
|
321
|
+
self.pos += 1
|
|
322
|
+
else:
|
|
323
|
+
break
|
|
324
|
+
|
|
325
|
+
text = self.source[start_pos:self.pos]
|
|
326
|
+
self.column += (self.pos - start_pos)
|
|
327
|
+
|
|
328
|
+
# 阶段二:精分
|
|
329
|
+
self._segment(text, start_col)
|
|
330
|
+
|
|
331
|
+
# ---- 阶段二:精分 ----
|
|
332
|
+
|
|
333
|
+
def _segment(self, text: str, start_col: int):
|
|
334
|
+
"""
|
|
335
|
+
正向最大匹配(Forward Maximum Matching)
|
|
336
|
+
|
|
337
|
+
对 text 中的每个位置,找最长的匹配关键字。
|
|
338
|
+
如果找不到关键字,发出单个字符作为 IDENTIFIER。
|
|
339
|
+
|
|
340
|
+
关键改进:使用位置指针 i 遍历 text,
|
|
341
|
+
每次从 i 开始找最长关键字。
|
|
342
|
+
找到后 i 跳过该关键字长度。
|
|
343
|
+
找不到时 i 前进 1(发出单个字符)。
|
|
344
|
+
|
|
345
|
+
标识符规则:连续 CJK 串优先整体为标识符(如「阶乘」含关键词「乘」,
|
|
346
|
+
但整体不是关键词 → 保持为标识符,避免误切分)。
|
|
347
|
+
"""
|
|
348
|
+
i = 0
|
|
349
|
+
col = start_col
|
|
350
|
+
|
|
351
|
+
while i < len(text):
|
|
352
|
+
# 尝试从位置 i 找最长关键字
|
|
353
|
+
matched_kw = None
|
|
354
|
+
matched_len = 0
|
|
355
|
+
|
|
356
|
+
for kw in SORTED_KW:
|
|
357
|
+
if text.startswith(kw, i):
|
|
358
|
+
if len(kw) > matched_len:
|
|
359
|
+
matched_kw = kw
|
|
360
|
+
matched_len = len(kw)
|
|
361
|
+
|
|
362
|
+
if matched_kw is not None:
|
|
363
|
+
# 发出关键字 token
|
|
364
|
+
self._emit(KEYWORD_MAP[matched_kw], matched_kw, col)
|
|
365
|
+
i += matched_len
|
|
366
|
+
col += matched_len
|
|
367
|
+
else:
|
|
368
|
+
# 不是关键字 → 收集连续的非关键字字符作为标识符
|
|
369
|
+
# 中文规则:连续 CJK 串优先整体为标识符(如「阶乘」含关键词「乘」,
|
|
370
|
+
# 但整串「阶乘」非关键词 → 保持整体,避免误切分)
|
|
371
|
+
ident_start = i
|
|
372
|
+
ident_col = col
|
|
373
|
+
|
|
374
|
+
if _is_cjk(text[i]):
|
|
375
|
+
while i < len(text) and _is_cjk(text[i]):
|
|
376
|
+
i += 1
|
|
377
|
+
col += 1
|
|
378
|
+
else:
|
|
379
|
+
while i < len(text):
|
|
380
|
+
ch = text[i]
|
|
381
|
+
has_kw_ahead = any(text.startswith(kw, i) for kw in SORTED_KW)
|
|
382
|
+
if has_kw_ahead:
|
|
383
|
+
break
|
|
384
|
+
i += 1
|
|
385
|
+
col += 1
|
|
386
|
+
|
|
387
|
+
ident = text[ident_start:i]
|
|
388
|
+
if ident:
|
|
389
|
+
self._emit(TokenType.IDENTIFIER, ident, ident_col)
|
|
390
|
+
|
|
391
|
+
# ---- 数字读取 ----
|
|
392
|
+
|
|
393
|
+
def _peek_isdigit(self) -> bool:
|
|
394
|
+
"""前瞻当前字符是否数字(多位数聚合判断)。"""
|
|
395
|
+
return self.pos + 1 < len(self.source) and self.source[self.pos + 1].isdigit()
|
|
396
|
+
|
|
397
|
+
def _read_number(self):
|
|
398
|
+
"""读取数值(支持整数、小数、负数)"""
|
|
399
|
+
start_col = self.column
|
|
400
|
+
result = []
|
|
401
|
+
|
|
402
|
+
# 负号
|
|
403
|
+
if self.source[self.pos] == "-":
|
|
404
|
+
result.append("-")
|
|
405
|
+
self.pos += 1
|
|
406
|
+
self.column += 1
|
|
407
|
+
|
|
408
|
+
# 整数部分
|
|
409
|
+
while self.pos < len(self.source) and self.source[self.pos].isdigit():
|
|
410
|
+
result.append(self.source[self.pos])
|
|
411
|
+
self.pos += 1
|
|
412
|
+
self.column += 1
|
|
413
|
+
|
|
414
|
+
# 小数部分
|
|
415
|
+
if self.pos < len(self.source) and self.source[self.pos] == ".":
|
|
416
|
+
result.append(".")
|
|
417
|
+
self.pos += 1
|
|
418
|
+
self.column += 1
|
|
419
|
+
while self.pos < len(self.source) and self.source[self.pos].isdigit():
|
|
420
|
+
result.append(self.source[self.pos])
|
|
421
|
+
self.pos += 1
|
|
422
|
+
self.column += 1
|
|
423
|
+
|
|
424
|
+
num_str = "".join(result)
|
|
425
|
+
try:
|
|
426
|
+
float(num_str)
|
|
427
|
+
self._emit(TokenType.NUMBER, num_str)
|
|
428
|
+
except ValueError:
|
|
429
|
+
self.errors.append(f"L{self.line}:C{start_col} 非法数值: '{num_str}'")
|
|
430
|
+
self._emit(TokenType.NUMBER, num_str)
|
|
431
|
+
|
|
432
|
+
# ---- 字符串读取 ----
|
|
433
|
+
|
|
434
|
+
def _read_string(self):
|
|
435
|
+
"""读取字符串"""
|
|
436
|
+
quote_char = self.source[self.pos]
|
|
437
|
+
end_quote = '"' if quote_char == '"' else "\u201d"
|
|
438
|
+
|
|
439
|
+
self.pos += 1
|
|
440
|
+
self.column += 1
|
|
441
|
+
result = []
|
|
442
|
+
|
|
443
|
+
while self.pos < len(self.source) and self.source[self.pos] != end_quote:
|
|
444
|
+
ch = self.source[self.pos]
|
|
445
|
+
if ch == "\n":
|
|
446
|
+
self.errors.append(f"L{self.line}:C{self.column} 字符串未闭合")
|
|
447
|
+
break
|
|
448
|
+
result.append(ch)
|
|
449
|
+
self.pos += 1
|
|
450
|
+
self.column += 1
|
|
451
|
+
|
|
452
|
+
if self.pos < len(self.source):
|
|
453
|
+
self.pos += 1 # 跳过结束引号
|
|
454
|
+
self.column += 1
|
|
455
|
+
|
|
456
|
+
self._emit(TokenType.STRING, "".join(result))
|
|
457
|
+
|
|
458
|
+
# ---- 注释跳过 ----
|
|
459
|
+
|
|
460
|
+
def _skip_comment(self):
|
|
461
|
+
"""跳过注释至本行结束。"""
|
|
462
|
+
while self.pos < len(self.source) and self.source[self.pos] != "\n":
|
|
463
|
+
self.pos += 1
|
|
464
|
+
|
|
465
|
+
# ---- Token 输出 ----
|
|
466
|
+
|
|
467
|
+
def _emit(self, token_type: TokenType, value: str, col: int = None):
|
|
468
|
+
"""输出一个 Token"""
|
|
469
|
+
c = col if col is not None else self.column
|
|
470
|
+
self.tokens.append(Token(token_type, value, self.line, c))
|
|
471
|
+
|
|
472
|
+
|
|
473
|
+
# =============================================================================
|
|
474
|
+
# 便捷函数
|
|
475
|
+
# =============================================================================
|
|
476
|
+
|
|
477
|
+
def tokenize(source: str) -> Tuple[List[Token], List[str]]:
|
|
478
|
+
"""便捷函数"""
|
|
479
|
+
lexer = Lexer(source)
|
|
480
|
+
return lexer.tokenize()
|
|
481
|
+
|
|
482
|
+
|
|
483
|
+
# =============================================================================
|
|
484
|
+
# 测试
|
|
485
|
+
# =============================================================================
|
|
486
|
+
|
|
487
|
+
if __name__ == "__main__":
|
|
488
|
+
test_code = """若条件空间为伴侣,则止情感权重于0.15。
|
|
489
|
+
道 新信任路径
|
|
490
|
+
问曰:如何验证信任?
|
|
491
|
+
答曰:信任值大于0.7。
|
|
492
|
+
术曰:1。德 累积信任值;2。自然 恢复默认。"""
|
|
493
|
+
|
|
494
|
+
print("=" * 60)
|
|
495
|
+
print("词法分析器 v2.0 测试")
|
|
496
|
+
print("=" * 60)
|
|
497
|
+
print(f"源代码:\n{test_code}\n")
|
|
498
|
+
|
|
499
|
+
tokens, errors = tokenize(test_code)
|
|
500
|
+
|
|
501
|
+
print("Token 序列:")
|
|
502
|
+
for t in tokens:
|
|
503
|
+
if t.type != TokenType.EOF:
|
|
504
|
+
print(f" {t}")
|
|
505
|
+
|
|
506
|
+
if errors:
|
|
507
|
+
print(f"\n错误:")
|
|
508
|
+
for e in errors:
|
|
509
|
+
print(f" ❌ {e}")
|
|
510
|
+
|
|
511
|
+
valid = len([t for t in tokens if t.type != TokenType.EOF])
|
|
512
|
+
print(f"\n总计:{valid} 个 Token,{len(errors)} 个错误")
|