Add files using upload-large-folder tool

LTA_openwebtext_dualt/logs/lta_lm1b_nosep_step1000_pos0_probe.log

@@ -0,0 +1,39 @@
+2026-05-25_15:24:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:25:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:25:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:26:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:26:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:27:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:27:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:28:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:28:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:29:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:29:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:30:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:30:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:31:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:31:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:32:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:32:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:33:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:33:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:34:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:34:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:35:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:35:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:36:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:36:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:37:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:37:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:38:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:38:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:39:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:39:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:40:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:40:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:41:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:41:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:42:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:42:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:43:20 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt
+2026-05-25_15:43:50 waiting runs/lta_lm1b_dirichlet_len1024_Cv_to_2v_nosep_gbs512_b32_4gpu_20k_save1k_gumbelwatch_20260525/step_0001000.pt

LTA_openwebtext_dualt/logs/lta_owt_c1024_gpt2_cached_exact100_repeat1024_4gpu_200step_small384x6_batchvalidwrong.log

@@ -0,0 +1,83 @@
+W0512 20:08:32.846000 241078 torch/distributed/run.py:792] 
+W0512 20:08:32.846000 241078 torch/distributed/run.py:792] *****************************************
+W0512 20:08:32.846000 241078 torch/distributed/run.py:792] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+W0512 20:08:32.846000 241078 torch/distributed/run.py:792] *****************************************
+[rank0]:[W512 20:08:34.635036290 ProcessGroupNCCL.cpp:4571] [PG ID 0 PG GUID 0 Rank 0]  using GPU 0 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
+[rank3]:[W512 20:08:34.675343368 ProcessGroupNCCL.cpp:4571] [PG ID 0 PG GUID 0 Rank 3]  using GPU 3 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
+[rank1]:[W512 20:08:34.704311615 ProcessGroupNCCL.cpp:4571] [PG ID 0 PG GUID 0 Rank 1]  using GPU 1 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
+[rank2]:[W512 20:08:34.712623507 ProcessGroupNCCL.cpp:4571] [PG ID 0 PG GUID 0 Rank 2]  using GPU 2 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. Specify device_ids in barrier() to force use of a particular device, or call init_process_group() with a device_id.
+{
+  "device": "cuda:0",
+  "rank": 0,
+  "world_size": 4,
+  "samples": "owt_cached_chunks:100",
+  "vocab_size": 50257,
+  "save_dir": "runs/lta_owt_c1024_gpt2_cached_exact100_repeat1024_4gpu_200step_small384x6_batchvalidwrong",
+  "batch_size": 16,
+  "grad_accum": 8,
+  "effective_batch_size": 512,
+  "global_batch_size": 512,
+  "lr_schedule": "constant_warmup",
+  "warmup_steps": 20,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_eps": 1e-08,
+  "model_type": "ddit",
+  "dual_t": true,
+  "corrupt_t_mode": "independent",
+  "corrupt_min_t": null,
+  "corrupt_max_t": null,
+  "dirichlet_endpoint_mode": "categorical_dual_t",
+  "dirichlet_semantic_t_mode": "same",
+  "dirichlet_semantic_t_value": 0.0,
+  "categorical_wrong_from_full_vocab": false,
+  "categorical_wrong_from_batch_valid_tokens": true,
+  "simplex_bridge_sampler": "dirichlet",
+  "logistic_normal_sigma_min": 0.18,
+  "logistic_normal_sigma_max": 2.2,
+  "logistic_normal_tau_min": 0.65,
+  "logistic_normal_tau_max": 1.15,
+  "torch_compile": false,
+  "compile_mode": "max-autotune",
+  "state_format": "prob",
+  "target_loss": "hard_ce",
+  "meanflow_weight": 0.0,
+  "bridge_noise_init": "logistic_normal",
+  "noise_sigma": -1.0,
+  "wrap": true,
+  "wrap_mode": "stream",
+  "wrap_record_buffer_size": 200,
+  "owt_cached_chunks": true,
+  "owt_chunk_cache_dir": "/e2e-data/evad-tech-vla/wanghan58/data/small_benchmarks/langflow_2604_11748/openwebtext_lta_cached_chunks/gpt2_len1024_train_minus_100k_exact100",
+  "owt_chunk_cache_rebuild": false,
+  "owt_chunk_cache_write_batch": 4096,
+  "owt_exact_repeat_per_chunk": 1024,
+  "online_chunk_shuffle": false,
+  "online_chunk_shuffle_buffer": 10000,
+  "openwebtext_split": "train_minus_100k",
+  "detokenizer": "auto",
+  "resolved_detokenizer": null,
+  "num_workers": 0,
+  "latest_every": 50,
+  "resume_path": ""
+}
+step=10 micro_steps=80 elapsed=17.9s lr=1.650000e-04 loss_all=10.7520 acc_all=0.6379 loss_corrupt=10.7665 acc_corrupt=0.4317 corrupt_frac=0.5586 loss=10.7665 loss_recon=10.7665 loss_meanflow=0.0000 mean_model_t=0.4965 mean_corrupt_t=0.5027 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4951 init_acc_corrupt=0.4700 init_gold_top10=0.4988 init_gold_top100=0.5290
+step=20 micro_steps=160 elapsed=17.4s lr=3.000000e-04 loss_all=10.0640 acc_all=0.2622 loss_corrupt=10.0881 acc_corrupt=0.1638 corrupt_frac=0.5436 loss=10.0881 loss_recon=10.0881 loss_meanflow=0.0000 mean_model_t=0.5053 mean_corrupt_t=0.5007 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4917 init_acc_corrupt=0.4748 init_gold_top10=0.5028 init_gold_top100=0.5310
+step=30 micro_steps=240 elapsed=17.4s lr=3.000000e-04 loss_all=8.5907 acc_all=0.0667 loss_corrupt=8.6036 acc_corrupt=0.0557 corrupt_frac=0.5511 loss=8.6036 loss_recon=8.6036 loss_meanflow=0.0000 mean_model_t=0.5046 mean_corrupt_t=0.4955 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4990 init_acc_corrupt=0.4640 init_gold_top10=0.4952 init_gold_top100=0.5250
+step=40 micro_steps=320 elapsed=17.4s lr=3.000000e-04 loss_all=7.4232 acc_all=0.0992 loss_corrupt=7.4581 acc_corrupt=0.0758 corrupt_frac=0.5403 loss=7.4581 loss_recon=7.4581 loss_meanflow=0.0000 mean_model_t=0.5071 mean_corrupt_t=0.5044 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4962 init_acc_corrupt=0.4710 init_gold_top10=0.4983 init_gold_top100=0.5262
+step=50 micro_steps=400 elapsed=17.4s lr=3.000000e-04 loss_all=6.7747 acc_all=0.1536 loss_corrupt=6.9464 acc_corrupt=0.1138 corrupt_frac=0.5425 loss=6.9464 loss_recon=6.9464 loss_meanflow=0.0000 mean_model_t=0.5009 mean_corrupt_t=0.5094 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4919 init_acc_corrupt=0.4734 init_gold_top10=0.5024 init_gold_top100=0.5309
+step=60 micro_steps=480 elapsed=18.1s lr=3.000000e-04 loss_all=5.8968 acc_all=0.2070 loss_corrupt=6.4232 acc_corrupt=0.1466 corrupt_frac=0.5551 loss=6.4232 loss_recon=6.4232 loss_meanflow=0.0000 mean_model_t=0.4866 mean_corrupt_t=0.4882 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.5221 init_acc_corrupt=0.4399 init_gold_top10=0.4717 init_gold_top100=0.5046
+step=70 micro_steps=560 elapsed=17.4s lr=3.000000e-04 loss_all=4.1907 acc_all=0.4661 loss_corrupt=5.3401 acc_corrupt=0.3180 corrupt_frac=0.5530 loss=5.3401 loss_recon=5.3401 loss_meanflow=0.0000 mean_model_t=0.5096 mean_corrupt_t=0.5101 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4880 init_acc_corrupt=0.4800 init_gold_top10=0.5069 init_gold_top100=0.5339
+step=80 micro_steps=640 elapsed=17.4s lr=3.000000e-04 loss_all=2.9934 acc_all=0.6596 loss_corrupt=4.7849 acc_corrupt=0.4321 corrupt_frac=0.5458 loss=4.7849 loss_recon=4.7849 loss_meanflow=0.0000 mean_model_t=0.5029 mean_corrupt_t=0.4971 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.5064 init_acc_corrupt=0.4564 init_gold_top10=0.4874 init_gold_top100=0.5181
+step=90 micro_steps=720 elapsed=17.4s lr=3.000000e-04 loss_all=2.6839 acc_all=0.6965 loss_corrupt=4.4455 acc_corrupt=0.4660 corrupt_frac=0.5379 loss=4.4455 loss_recon=4.4455 loss_meanflow=0.0000 mean_model_t=0.4860 mean_corrupt_t=0.5105 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4883 init_acc_corrupt=0.4772 init_gold_top10=0.5057 init_gold_top100=0.5341
+step=100 micro_steps=800 elapsed=17.4s lr=3.000000e-04 loss_all=2.6332 acc_all=0.7055 loss_corrupt=4.4267 acc_corrupt=0.4659 corrupt_frac=0.5472 loss=4.4267 loss_recon=4.4267 loss_meanflow=0.0000 mean_model_t=0.5105 mean_corrupt_t=0.4932 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.5055 init_acc_corrupt=0.4587 init_gold_top10=0.4886 init_gold_top100=0.5190
+step=110 micro_steps=880 elapsed=18.7s lr=3.000000e-04 loss_all=2.5071 acc_all=0.7149 loss_corrupt=4.2114 acc_corrupt=0.4882 corrupt_frac=0.5545 loss=4.2114 loss_recon=4.2114 loss_meanflow=0.0000 mean_model_t=0.5036 mean_corrupt_t=0.5111 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4856 init_acc_corrupt=0.4813 init_gold_top10=0.5091 init_gold_top100=0.5364
+step=120 micro_steps=960 elapsed=17.4s lr=3.000000e-04 loss_all=2.4989 acc_all=0.7103 loss_corrupt=4.2859 acc_corrupt=0.4678 corrupt_frac=0.5444 loss=4.2859 loss_recon=4.2859 loss_meanflow=0.0000 mean_model_t=0.5067 mean_corrupt_t=0.4960 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.5054 init_acc_corrupt=0.4600 init_gold_top10=0.4886 init_gold_top100=0.5183
+step=130 micro_steps=1040 elapsed=17.4s lr=3.000000e-04 loss_all=2.3946 acc_all=0.7167 loss_corrupt=4.1501 acc_corrupt=0.4788 corrupt_frac=0.5411 loss=4.1501 loss_recon=4.1501 loss_meanflow=0.0000 mean_model_t=0.5008 mean_corrupt_t=0.5035 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4966 init_acc_corrupt=0.4691 init_gold_top10=0.4977 init_gold_top100=0.5270
+step=140 micro_steps=1120 elapsed=17.4s lr=3.000000e-04 loss_all=2.4375 acc_all=0.7048 loss_corrupt=4.1514 acc_corrupt=0.4716 corrupt_frac=0.5580 loss=4.1514 loss_recon=4.1514 loss_meanflow=0.0000 mean_model_t=0.4983 mean_corrupt_t=0.4959 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.5046 init_acc_corrupt=0.4610 init_gold_top10=0.4895 init_gold_top100=0.5205
+step=150 micro_steps=1200 elapsed=17.4s lr=3.000000e-04 loss_all=2.2902 acc_all=0.7165 loss_corrupt=3.9504 acc_corrupt=0.4876 corrupt_frac=0.5521 loss=3.9504 loss_recon=3.9504 loss_meanflow=0.0000 mean_model_t=0.5027 mean_corrupt_t=0.5028 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4911 init_acc_corrupt=0.4772 init_gold_top10=0.5034 init_gold_top100=0.5311
+step=160 micro_steps=1280 elapsed=18.0s lr=3.000000e-04 loss_all=2.2115 acc_all=0.7206 loss_corrupt=3.9186 acc_corrupt=0.4821 corrupt_frac=0.5398 loss=3.9186 loss_recon=3.9186 loss_meanflow=0.0000 mean_model_t=0.5008 mean_corrupt_t=0.5052 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4946 init_acc_corrupt=0.4708 init_gold_top10=0.4994 init_gold_top100=0.5294
+step=170 micro_steps=1360 elapsed=17.4s lr=3.000000e-04 loss_all=2.2306 acc_all=0.7119 loss_corrupt=3.8726 acc_corrupt=0.4791 corrupt_frac=0.5507 loss=3.8726 loss_recon=3.8726 loss_meanflow=0.0000 mean_model_t=0.5059 mean_corrupt_t=0.5007 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4967 init_acc_corrupt=0.4668 init_gold_top10=0.4975 init_gold_top100=0.5268
+step=180 micro_steps=1440 elapsed=17.4s lr=3.000000e-04 loss_all=2.2149 acc_all=0.7080 loss_corrupt=3.8057 acc_corrupt=0.4794 corrupt_frac=0.5600 loss=3.8057 loss_recon=3.8057 loss_meanflow=0.0000 mean_model_t=0.5141 mean_corrupt_t=0.5011 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4974 init_acc_corrupt=0.4651 init_gold_top10=0.4964 init_gold_top100=0.5273
+step=190 micro_steps=1520 elapsed=17.4s lr=3.000000e-04 loss_all=2.2150 acc_all=0.7051 loss_corrupt=3.8357 acc_corrupt=0.4713 corrupt_frac=0.5590 loss=3.8357 loss_recon=3.8357 loss_meanflow=0.0000 mean_model_t=0.4854 mean_corrupt_t=0.4936 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.5086 init_acc_corrupt=0.4567 init_gold_top10=0.4856 init_gold_top100=0.5141
+step=200 micro_steps=1600 elapsed=17.4s lr=3.000000e-04 loss_all=2.0763 acc_all=0.7206 loss_corrupt=3.7013 acc_corrupt=0.4838 corrupt_frac=0.5418 loss=3.7013 loss_recon=3.7013 loss_meanflow=0.0000 mean_model_t=0.4878 mean_corrupt_t=0.5033 mean_loss_t_weight=1.0000 prior_center_loss_beta=0.0000 wrong_frac=0.4982 init_acc_corrupt=0.4673 init_gold_top10=0.4961 init_gold_top100=0.5249

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/_sourcemod_builtins.py

@@ -0,0 +1,1151 @@
+"""
+    pygments.lexers._sourcemod_builtins
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    This file contains the names of SourceMod functions.
+
+    Do not edit the FUNCTIONS list by hand.
+
+    Run with `python -I` to regenerate.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+FUNCTIONS = (
+    'OnEntityCreated',
+    'OnEntityDestroyed',
+    'OnGetGameDescription',
+    'OnLevelInit',
+    'SDKHook',
+    'SDKHookEx',
+    'SDKUnhook',
+    'SDKHooks_TakeDamage',
+    'SDKHooks_DropWeapon',
+    'TopMenuHandler',
+    'CreateTopMenu',
+    'LoadTopMenuConfig',
+    'AddToTopMenu',
+    'GetTopMenuInfoString',
+    'GetTopMenuObjName',
+    'RemoveFromTopMenu',
+    'DisplayTopMenu',
+    'DisplayTopMenuCategory',
+    'FindTopMenuCategory',
+    'SetTopMenuTitleCaching',
+    'OnAdminMenuCreated',
+    'OnAdminMenuReady',
+    'GetAdminTopMenu',
+    'AddTargetsToMenu',
+    'AddTargetsToMenu2',
+    'RedisplayAdminMenu',
+    'TEHook',
+    'AddTempEntHook',
+    'RemoveTempEntHook',
+    'TE_Start',
+    'TE_IsValidProp',
+    'TE_WriteNum',
+    'TE_ReadNum',
+    'TE_WriteFloat',
+    'TE_ReadFloat',
+    'TE_WriteVector',
+    'TE_ReadVector',
+    'TE_WriteAngles',
+    'TE_WriteFloatArray',
+    'TE_Send',
+    'TE_WriteEncodedEnt',
+    'TE_SendToAll',
+    'TE_SendToClient',
+    'CreateKeyValues',
+    'KvSetString',
+    'KvSetNum',
+    'KvSetUInt64',
+    'KvSetFloat',
+    'KvSetColor',
+    'KvSetVector',
+    'KvGetString',
+    'KvGetNum',
+    'KvGetFloat',
+    'KvGetColor',
+    'KvGetUInt64',
+    'KvGetVector',
+    'KvJumpToKey',
+    'KvJumpToKeySymbol',
+    'KvGotoFirstSubKey',
+    'KvGotoNextKey',
+    'KvSavePosition',
+    'KvDeleteKey',
+    'KvDeleteThis',
+    'KvGoBack',
+    'KvRewind',
+    'KvGetSectionName',
+    'KvSetSectionName',
+    'KvGetDataType',
+    'KeyValuesToFile',
+    'FileToKeyValues',
+    'StringToKeyValues',
+    'KvSetEscapeSequences',
+    'KvNodesInStack',
+    'KvCopySubkeys',
+    'KvFindKeyById',
+    'KvGetNameSymbol',
+    'KvGetSectionSymbol',
+    'TE_SetupSparks',
+    'TE_SetupSmoke',
+    'TE_SetupDust',
+    'TE_SetupMuzzleFlash',
+    'TE_SetupMetalSparks',
+    'TE_SetupEnergySplash',
+    'TE_SetupArmorRicochet',
+    'TE_SetupGlowSprite',
+    'TE_SetupExplosion',
+    'TE_SetupBloodSprite',
+    'TE_SetupBeamRingPoint',
+    'TE_SetupBeamPoints',
+    'TE_SetupBeamLaser',
+    'TE_SetupBeamRing',
+    'TE_SetupBeamFollow',
+    'HookEvent',
+    'HookEventEx',
+    'UnhookEvent',
+    'CreateEvent',
+    'FireEvent',
+    'CancelCreatedEvent',
+    'GetEventBool',
+    'SetEventBool',
+    'GetEventInt',
+    'SetEventInt',
+    'GetEventFloat',
+    'SetEventFloat',
+    'GetEventString',
+    'SetEventString',
+    'GetEventName',
+    'SetEventBroadcast',
+    'GetUserMessageType',
+    'GetUserMessageId',
+    'GetUserMessageName',
+    'StartMessage',
+    'StartMessageEx',
+    'EndMessage',
+    'MsgHook',
+    'MsgPostHook',
+    'HookUserMessage',
+    'UnhookUserMessage',
+    'StartMessageAll',
+    'StartMessageOne',
+    'InactivateClient',
+    'ReconnectClient',
+    'GetMaxEntities',
+    'GetEntityCount',
+    'IsValidEntity',
+    'IsValidEdict',
+    'IsEntNetworkable',
+    'CreateEdict',
+    'RemoveEdict',
+    'GetEdictFlags',
+    'SetEdictFlags',
+    'GetEdictClassname',
+    'GetEntityNetClass',
+    'ChangeEdictState',
+    'GetEntData',
+    'SetEntData',
+    'GetEntDataFloat',
+    'SetEntDataFloat',
+    'GetEntDataEnt2',
+    'SetEntDataEnt2',
+    'GetEntDataVector',
+    'SetEntDataVector',
+    'GetEntDataString',
+    'SetEntDataString',
+    'FindSendPropOffs',
+    'FindSendPropInfo',
+    'FindDataMapOffs',
+    'FindDataMapInfo',
+    'GetEntSendPropOffs',
+    'GetEntProp',
+    'SetEntProp',
+    'GetEntPropFloat',
+    'SetEntPropFloat',
+    'GetEntPropEnt',
+    'SetEntPropEnt',
+    'GetEntPropVector',
+    'SetEntPropVector',
+    'GetEntPropString',
+    'SetEntPropString',
+    'GetEntPropArraySize',
+    'GetEntDataArray',
+    'SetEntDataArray',
+    'GetEntityAddress',
+    'GetEntityClassname',
+    'float',
+    'FloatMul',
+    'FloatDiv',
+    'FloatAdd',
+    'FloatSub',
+    'FloatFraction',
+    'RoundToZero',
+    'RoundToCeil',
+    'RoundToFloor',
+    'RoundToNearest',
+    'FloatCompare',
+    'SquareRoot',
+    'Pow',
+    'Exponential',
+    'Logarithm',
+    'Sine',
+    'Cosine',
+    'Tangent',
+    'FloatAbs',
+    'ArcTangent',
+    'ArcCosine',
+    'ArcSine',
+    'ArcTangent2',
+    'RoundFloat',
+    'operator%',
+    'DegToRad',
+    'RadToDeg',
+    'GetURandomInt',
+    'GetURandomFloat',
+    'SetURandomSeed',
+    'SetURandomSeedSimple',
+    'RemovePlayerItem',
+    'GivePlayerItem',
+    'GetPlayerWeaponSlot',
+    'IgniteEntity',
+    'ExtinguishEntity',
+    'TeleportEntity',
+    'ForcePlayerSuicide',
+    'SlapPlayer',
+    'FindEntityByClassname',
+    'GetClientEyeAngles',
+    'CreateEntityByName',
+    'DispatchSpawn',
+    'DispatchKeyValue',
+    'DispatchKeyValueFloat',
+    'DispatchKeyValueVector',
+    'GetClientAimTarget',
+    'GetTeamCount',
+    'GetTeamName',
+    'GetTeamScore',
+    'SetTeamScore',
+    'GetTeamClientCount',
+    'SetEntityModel',
+    'GetPlayerDecalFile',
+    'GetPlayerJingleFile',
+    'GetServerNetStats',
+    'EquipPlayerWeapon',
+    'ActivateEntity',
+    'SetClientInfo',
+    'GivePlayerAmmo',
+    'SetClientListeningFlags',
+    'GetClientListeningFlags',
+    'SetListenOverride',
+    'GetListenOverride',
+    'IsClientMuted',
+    'TR_GetPointContents',
+    'TR_GetPointContentsEnt',
+    'TR_TraceRay',
+    'TR_TraceHull',
+    'TR_TraceRayFilter',
+    'TR_TraceHullFilter',
+    'TR_TraceRayEx',
+    'TR_TraceHullEx',
+    'TR_TraceRayFilterEx',
+    'TR_TraceHullFilterEx',
+    'TR_GetFraction',
+    'TR_GetEndPosition',
+    'TR_GetEntityIndex',
+    'TR_DidHit',
+    'TR_GetHitGroup',
+    'TR_GetPlaneNormal',
+    'TR_PointOutsideWorld',
+    'SortIntegers',
+    'SortFloats',
+    'SortStrings',
+    'SortFunc1D',
+    'SortCustom1D',
+    'SortCustom2D',
+    'SortADTArray',
+    'SortFuncADTArray',
+    'SortADTArrayCustom',
+    'CompileRegex',
+    'MatchRegex',
+    'GetRegexSubString',
+    'SimpleRegexMatch',
+    'TF2_GetPlayerClass',
+    'TF2_SetPlayerClass',
+    'TF2_RemoveWeaponSlot',
+    'TF2_RemoveAllWeapons',
+    'TF2_IsPlayerInCondition',
+    'TF2_GetObjectType',
+    'TF2_GetObjectMode',
+    'NominateMap',
+    'RemoveNominationByMap',
+    'RemoveNominationByOwner',
+    'GetExcludeMapList',
+    'GetNominatedMapList',
+    'CanMapChooserStartVote',
+    'InitiateMapChooserVote',
+    'HasEndOfMapVoteFinished',
+    'EndOfMapVoteEnabled',
+    'OnNominationRemoved',
+    'OnMapVoteStarted',
+    'CreateTimer',
+    'KillTimer',
+    'TriggerTimer',
+    'GetTickedTime',
+    'GetMapTimeLeft',
+    'GetMapTimeLimit',
+    'ExtendMapTimeLimit',
+    'GetTickInterval',
+    'OnMapTimeLeftChanged',
+    'IsServerProcessing',
+    'CreateDataTimer',
+    'ByteCountToCells',
+    'CreateArray',
+    'ClearArray',
+    'CloneArray',
+    'ResizeArray',
+    'GetArraySize',
+    'PushArrayCell',
+    'PushArrayString',
+    'PushArrayArray',
+    'GetArrayCell',
+    'GetArrayString',
+    'GetArrayArray',
+    'SetArrayCell',
+    'SetArrayString',
+    'SetArrayArray',
+    'ShiftArrayUp',
+    'RemoveFromArray',
+    'SwapArrayItems',
+    'FindStringInArray',
+    'FindValueInArray',
+    'ProcessTargetString',
+    'ReplyToTargetError',
+    'MultiTargetFilter',
+    'AddMultiTargetFilter',
+    'RemoveMultiTargetFilter',
+    'OnBanClient',
+    'OnBanIdentity',
+    'OnRemoveBan',
+    'BanClient',
+    'BanIdentity',
+    'RemoveBan',
+    'CreateTrie',
+    'SetTrieValue',
+    'SetTrieArray',
+    'SetTrieString',
+    'GetTrieValue',
+    'GetTrieArray',
+    'GetTrieString',
+    'RemoveFromTrie',
+    'ClearTrie',
+    'GetTrieSize',
+    'GetFunctionByName',
+    'CreateGlobalForward',
+    'CreateForward',
+    'GetForwardFunctionCount',
+    'AddToForward',
+    'RemoveFromForward',
+    'RemoveAllFromForward',
+    'Call_StartForward',
+    'Call_StartFunction',
+    'Call_PushCell',
+    'Call_PushCellRef',
+    'Call_PushFloat',
+    'Call_PushFloatRef',
+    'Call_PushArray',
+    'Call_PushArrayEx',
+    'Call_PushString',
+    'Call_PushStringEx',
+    'Call_Finish',
+    'Call_Cancel',
+    'NativeCall',
+    'CreateNative',
+    'ThrowNativeError',
+    'GetNativeStringLength',
+    'GetNativeString',
+    'SetNativeString',
+    'GetNativeCell',
+    'GetNativeCellRef',
+    'SetNativeCellRef',
+    'GetNativeArray',
+    'SetNativeArray',
+    'FormatNativeString',
+    'RequestFrameCallback',
+    'RequestFrame',
+    'OnRebuildAdminCache',
+    'DumpAdminCache',
+    'AddCommandOverride',
+    'GetCommandOverride',
+    'UnsetCommandOverride',
+    'CreateAdmGroup',
+    'FindAdmGroup',
+    'SetAdmGroupAddFlag',
+    'GetAdmGroupAddFlag',
+    'GetAdmGroupAddFlags',
+    'SetAdmGroupImmuneFrom',
+    'GetAdmGroupImmuneCount',
+    'GetAdmGroupImmuneFrom',
+    'AddAdmGroupCmdOverride',
+    'GetAdmGroupCmdOverride',
+    'RegisterAuthIdentType',
+    'CreateAdmin',
+    'GetAdminUsername',
+    'BindAdminIdentity',
+    'SetAdminFlag',
+    'GetAdminFlag',
+    'GetAdminFlags',
+    'AdminInheritGroup',
+    'GetAdminGroupCount',
+    'GetAdminGroup',
+    'SetAdminPassword',
+    'GetAdminPassword',
+    'FindAdminByIdentity',
+    'RemoveAdmin',
+    'FlagBitsToBitArray',
+    'FlagBitArrayToBits',
+    'FlagArrayToBits',
+    'FlagBitsToArray',
+    'FindFlagByName',
+    'FindFlagByChar',
+    'FindFlagChar',
+    'ReadFlagString',
+    'CanAdminTarget',
+    'CreateAuthMethod',
+    'SetAdmGroupImmunityLevel',
+    'GetAdmGroupImmunityLevel',
+    'SetAdminImmunityLevel',
+    'GetAdminImmunityLevel',
+    'FlagToBit',
+    'BitToFlag',
+    'ServerCommand',
+    'ServerCommandEx',
+    'InsertServerCommand',
+    'ServerExecute',
+    'ClientCommand',
+    'FakeClientCommand',
+    'FakeClientCommandEx',
+    'PrintToServer',
+    'PrintToConsole',
+    'ReplyToCommand',
+    'GetCmdReplySource',
+    'SetCmdReplySource',
+    'IsChatTrigger',
+    'ShowActivity2',
+    'ShowActivity',
+    'ShowActivityEx',
+    'FormatActivitySource',
+    'SrvCmd',
+    'RegServerCmd',
+    'ConCmd',
+    'RegConsoleCmd',
+    'RegAdminCmd',
+    'GetCmdArgs',
+    'GetCmdArg',
+    'GetCmdArgString',
+    'CreateConVar',
+    'FindConVar',
+    'ConVarChanged',
+    'HookConVarChange',
+    'UnhookConVarChange',
+    'GetConVarBool',
+    'SetConVarBool',
+    'GetConVarInt',
+    'SetConVarInt',
+    'GetConVarFloat',
+    'SetConVarFloat',
+    'GetConVarString',
+    'SetConVarString',
+    'ResetConVar',
+    'GetConVarDefault',
+    'GetConVarFlags',
+    'SetConVarFlags',
+    'GetConVarBounds',
+    'SetConVarBounds',
+    'GetConVarName',
+    'QueryClientConVar',
+    'GetCommandIterator',
+    'ReadCommandIterator',
+    'CheckCommandAccess',
+    'CheckAccess',
+    'IsValidConVarChar',
+    'GetCommandFlags',
+    'SetCommandFlags',
+    'FindFirstConCommand',
+    'FindNextConCommand',
+    'SendConVarValue',
+    'AddServerTag',
+    'RemoveServerTag',
+    'CommandListener',
+    'AddCommandListener',
+    'RemoveCommandListener',
+    'CommandExists',
+    'OnClientSayCommand',
+    'OnClientSayCommand_Post',
+    'TF2_IgnitePlayer',
+    'TF2_RespawnPlayer',
+    'TF2_RegeneratePlayer',
+    'TF2_AddCondition',
+    'TF2_RemoveCondition',
+    'TF2_SetPlayerPowerPlay',
+    'TF2_DisguisePlayer',
+    'TF2_RemovePlayerDisguise',
+    'TF2_StunPlayer',
+    'TF2_MakeBleed',
+    'TF2_GetClass',
+    'TF2_CalcIsAttackCritical',
+    'TF2_OnIsHolidayActive',
+    'TF2_IsHolidayActive',
+    'TF2_IsPlayerInDuel',
+    'TF2_RemoveWearable',
+    'TF2_OnConditionAdded',
+    'TF2_OnConditionRemoved',
+    'TF2_OnWaitingForPlayersStart',
+    'TF2_OnWaitingForPlayersEnd',
+    'TF2_OnPlayerTeleport',
+    'SQL_Connect',
+    'SQL_DefConnect',
+    'SQL_ConnectCustom',
+    'SQLite_UseDatabase',
+    'SQL_CheckConfig',
+    'SQL_GetDriver',
+    'SQL_ReadDriver',
+    'SQL_GetDriverIdent',
+    'SQL_GetDriverProduct',
+    'SQL_SetCharset',
+    'SQL_GetAffectedRows',
+    'SQL_GetInsertId',
+    'SQL_GetError',
+    'SQL_EscapeString',
+    'SQL_QuoteString',
+    'SQL_FastQuery',
+    'SQL_Query',
+    'SQL_PrepareQuery',
+    'SQL_FetchMoreResults',
+    'SQL_HasResultSet',
+    'SQL_GetRowCount',
+    'SQL_GetFieldCount',
+    'SQL_FieldNumToName',
+    'SQL_FieldNameToNum',
+    'SQL_FetchRow',
+    'SQL_MoreRows',
+    'SQL_Rewind',
+    'SQL_FetchString',
+    'SQL_FetchFloat',
+    'SQL_FetchInt',
+    'SQL_IsFieldNull',
+    'SQL_FetchSize',
+    'SQL_BindParamInt',
+    'SQL_BindParamFloat',
+    'SQL_BindParamString',
+    'SQL_Execute',
+    'SQL_LockDatabase',
+    'SQL_UnlockDatabase',
+    'SQLTCallback',
+    'SQL_IsSameConnection',
+    'SQL_TConnect',
+    'SQL_TQuery',
+    'SQL_CreateTransaction',
+    'SQL_AddQuery',
+    'SQLTxnSuccess',
+    'SQLTxnFailure',
+    'SQL_ExecuteTransaction',
+    'CloseHandle',
+    'CloneHandle',
+    'MenuHandler',
+    'CreateMenu',
+    'DisplayMenu',
+    'DisplayMenuAtItem',
+    'AddMenuItem',
+    'InsertMenuItem',
+    'RemoveMenuItem',
+    'RemoveAllMenuItems',
+    'GetMenuItem',
+    'GetMenuSelectionPosition',
+    'GetMenuItemCount',
+    'SetMenuPagination',
+    'GetMenuPagination',
+    'GetMenuStyle',
+    'SetMenuTitle',
+    'GetMenuTitle',
+    'CreatePanelFromMenu',
+    'GetMenuExitButton',
+    'SetMenuExitButton',
+    'GetMenuExitBackButton',
+    'SetMenuExitBackButton',
+    'SetMenuNoVoteButton',
+    'CancelMenu',
+    'GetMenuOptionFlags',
+    'SetMenuOptionFlags',
+    'IsVoteInProgress',
+    'CancelVote',
+    'VoteMenu',
+    'VoteMenuToAll',
+    'VoteHandler',
+    'SetVoteResultCallback',
+    'CheckVoteDelay',
+    'IsClientInVotePool',
+    'RedrawClientVoteMenu',
+    'GetMenuStyleHandle',
+    'CreatePanel',
+    'CreateMenuEx',
+    'GetClientMenu',
+    'CancelClientMenu',
+    'GetMaxPageItems',
+    'GetPanelStyle',
+    'SetPanelTitle',
+    'DrawPanelItem',
+    'DrawPanelText',
+    'CanPanelDrawFlags',
+    'SetPanelKeys',
+    'SendPanelToClient',
+    'GetPanelTextRemaining',
+    'GetPanelCurrentKey',
+    'SetPanelCurrentKey',
+    'RedrawMenuItem',
+    'InternalShowMenu',
+    'GetMenuVoteInfo',
+    'IsNewVoteAllowed',
+    'PrefetchSound',
+    'EmitAmbientSound',
+    'FadeClientVolume',
+    'StopSound',
+    'EmitSound',
+    'EmitSentence',
+    'GetDistGainFromSoundLevel',
+    'AmbientSHook',
+    'NormalSHook',
+    'AddAmbientSoundHook',
+    'AddNormalSoundHook',
+    'RemoveAmbientSoundHook',
+    'RemoveNormalSoundHook',
+    'EmitSoundToClient',
+    'EmitSoundToAll',
+    'ATTN_TO_SNDLEVEL',
+    'GetGameSoundParams',
+    'EmitGameSound',
+    'EmitAmbientGameSound',
+    'EmitGameSoundToClient',
+    'EmitGameSoundToAll',
+    'PrecacheScriptSound',
+    'strlen',
+    'StrContains',
+    'strcmp',
+    'strncmp',
+    'StrEqual',
+    'strcopy',
+    'Format',
+    'FormatEx',
+    'VFormat',
+    'StringToInt',
+    'StringToIntEx',
+    'IntToString',
+    'StringToFloat',
+    'StringToFloatEx',
+    'FloatToString',
+    'BreakString',
+    'TrimString',
+    'SplitString',
+    'ReplaceString',
+    'ReplaceStringEx',
+    'GetCharBytes',
+    'IsCharAlpha',
+    'IsCharNumeric',
+    'IsCharSpace',
+    'IsCharMB',
+    'IsCharUpper',
+    'IsCharLower',
+    'StripQuotes',
+    'CharToUpper',
+    'CharToLower',
+    'FindCharInString',
+    'StrCat',
+    'ExplodeString',
+    'ImplodeStrings',
+    'GetVectorLength',
+    'GetVectorDistance',
+    'GetVectorDotProduct',
+    'GetVectorCrossProduct',
+    'NormalizeVector',
+    'GetAngleVectors',
+    'GetVectorAngles',
+    'GetVectorVectors',
+    'AddVectors',
+    'SubtractVectors',
+    'ScaleVector',
+    'NegateVector',
+    'MakeVectorFromPoints',
+    'BaseComm_IsClientGagged',
+    'BaseComm_IsClientMuted',
+    'BaseComm_SetClientGag',
+    'BaseComm_SetClientMute',
+    'FormatUserLogText',
+    'FindPluginByFile',
+    'FindTarget',
+    'AcceptEntityInput',
+    'SetVariantBool',
+    'SetVariantString',
+    'SetVariantInt',
+    'SetVariantFloat',
+    'SetVariantVector3D',
+    'SetVariantPosVector3D',
+    'SetVariantColor',
+    'SetVariantEntity',
+    'GameRules_GetProp',
+    'GameRules_SetProp',
+    'GameRules_GetPropFloat',
+    'GameRules_SetPropFloat',
+    'GameRules_GetPropEnt',
+    'GameRules_SetPropEnt',
+    'GameRules_GetPropVector',
+    'GameRules_SetPropVector',
+    'GameRules_GetPropString',
+    'GameRules_SetPropString',
+    'GameRules_GetRoundState',
+    'OnClientConnect',
+    'OnClientConnected',
+    'OnClientPutInServer',
+    'OnClientDisconnect',
+    'OnClientDisconnect_Post',
+    'OnClientCommand',
+    'OnClientSettingsChanged',
+    'OnClientAuthorized',
+    'OnClientPreAdminCheck',
+    'OnClientPostAdminFilter',
+    'OnClientPostAdminCheck',
+    'GetMaxClients',
+    'GetMaxHumanPlayers',
+    'GetClientCount',
+    'GetClientName',
+    'GetClientIP',
+    'GetClientAuthString',
+    'GetClientAuthId',
+    'GetSteamAccountID',
+    'GetClientUserId',
+    'IsClientConnected',
+    'IsClientInGame',
+    'IsClientInKickQueue',
+    'IsClientAuthorized',
+    'IsFakeClient',
+    'IsClientSourceTV',
+    'IsClientReplay',
+    'IsClientObserver',
+    'IsPlayerAlive',
+    'GetClientInfo',
+    'GetClientTeam',
+    'SetUserAdmin',
+    'GetUserAdmin',
+    'AddUserFlags',
+    'RemoveUserFlags',
+    'SetUserFlagBits',
+    'GetUserFlagBits',
+    'CanUserTarget',
+    'RunAdminCacheChecks',
+    'NotifyPostAdminCheck',
+    'CreateFakeClient',
+    'SetFakeClientConVar',
+    'GetClientHealth',
+    'GetClientModel',
+    'GetClientWeapon',
+    'GetClientMaxs',
+    'GetClientMins',
+    'GetClientAbsAngles',
+    'GetClientAbsOrigin',
+    'GetClientArmor',
+    'GetClientDeaths',
+    'GetClientFrags',
+    'GetClientDataRate',
+    'IsClientTimingOut',
+    'GetClientTime',
+    'GetClientLatency',
+    'GetClientAvgLatency',
+    'GetClientAvgLoss',
+    'GetClientAvgChoke',
+    'GetClientAvgData',
+    'GetClientAvgPackets',
+    'GetClientOfUserId',
+    'KickClient',
+    'KickClientEx',
+    'ChangeClientTeam',
+    'GetClientSerial',
+    'GetClientFromSerial',
+    'FindStringTable',
+    'GetNumStringTables',
+    'GetStringTableNumStrings',
+    'GetStringTableMaxStrings',
+    'GetStringTableName',
+    'FindStringIndex',
+    'ReadStringTable',
+    'GetStringTableDataLength',
+    'GetStringTableData',
+    'SetStringTableData',
+    'AddToStringTable',
+    'LockStringTables',
+    'AddFileToDownloadsTable',
+    'GetEntityFlags',
+    'SetEntityFlags',
+    'GetEntityMoveType',
+    'SetEntityMoveType',
+    'GetEntityRenderMode',
+    'SetEntityRenderMode',
+    'GetEntityRenderFx',
+    'SetEntityRenderFx',
+    'SetEntityRenderColor',
+    'GetEntityGravity',
+    'SetEntityGravity',
+    'SetEntityHealth',
+    'GetClientButtons',
+    'EntityOutput',
+    'HookEntityOutput',
+    'UnhookEntityOutput',
+    'HookSingleEntityOutput',
+    'UnhookSingleEntityOutput',
+    'SMC_CreateParser',
+    'SMC_ParseFile',
+    'SMC_GetErrorString',
+    'SMC_ParseStart',
+    'SMC_SetParseStart',
+    'SMC_ParseEnd',
+    'SMC_SetParseEnd',
+    'SMC_NewSection',
+    'SMC_KeyValue',
+    'SMC_EndSection',
+    'SMC_SetReaders',
+    'SMC_RawLine',
+    'SMC_SetRawLine',
+    'BfWriteBool',
+    'BfWriteByte',
+    'BfWriteChar',
+    'BfWriteShort',
+    'BfWriteWord',
+    'BfWriteNum',
+    'BfWriteFloat',
+    'BfWriteString',
+    'BfWriteEntity',
+    'BfWriteAngle',
+    'BfWriteCoord',
+    'BfWriteVecCoord',
+    'BfWriteVecNormal',
+    'BfWriteAngles',
+    'BfReadBool',
+    'BfReadByte',
+    'BfReadChar',
+    'BfReadShort',
+    'BfReadWord',
+    'BfReadNum',
+    'BfReadFloat',
+    'BfReadString',
+    'BfReadEntity',
+    'BfReadAngle',
+    'BfReadCoord',
+    'BfReadVecCoord',
+    'BfReadVecNormal',
+    'BfReadAngles',
+    'BfGetNumBytesLeft',
+    'CreateProfiler',
+    'StartProfiling',
+    'StopProfiling',
+    'GetProfilerTime',
+    'OnPluginStart',
+    'AskPluginLoad2',
+    'OnPluginEnd',
+    'OnPluginPauseChange',
+    'OnGameFrame',
+    'OnMapStart',
+    'OnMapEnd',
+    'OnConfigsExecuted',
+    'OnAutoConfigsBuffered',
+    'OnAllPluginsLoaded',
+    'GetMyHandle',
+    'GetPluginIterator',
+    'MorePlugins',
+    'ReadPlugin',
+    'GetPluginStatus',
+    'GetPluginFilename',
+    'IsPluginDebugging',
+    'GetPluginInfo',
+    'FindPluginByNumber',
+    'SetFailState',
+    'ThrowError',
+    'GetTime',
+    'FormatTime',
+    'LoadGameConfigFile',
+    'GameConfGetOffset',
+    'GameConfGetKeyValue',
+    'GameConfGetAddress',
+    'GetSysTickCount',
+    'AutoExecConfig',
+    'RegPluginLibrary',
+    'LibraryExists',
+    'GetExtensionFileStatus',
+    'OnLibraryAdded',
+    'OnLibraryRemoved',
+    'ReadMapList',
+    'SetMapListCompatBind',
+    'OnClientFloodCheck',
+    'OnClientFloodResult',
+    'CanTestFeatures',
+    'GetFeatureStatus',
+    'RequireFeature',
+    'LoadFromAddress',
+    'StoreToAddress',
+    'CreateStack',
+    'PushStackCell',
+    'PushStackString',
+    'PushStackArray',
+    'PopStackCell',
+    'PopStackString',
+    'PopStackArray',
+    'IsStackEmpty',
+    'PopStack',
+    'OnPlayerRunCmd',
+    'BuildPath',
+    'OpenDirectory',
+    'ReadDirEntry',
+    'OpenFile',
+    'DeleteFile',
+    'ReadFileLine',
+    'ReadFile',
+    'ReadFileString',
+    'WriteFile',
+    'WriteFileString',
+    'WriteFileLine',
+    'ReadFileCell',
+    'WriteFileCell',
+    'IsEndOfFile',
+    'FileSeek',
+    'FilePosition',
+    'FileExists',
+    'RenameFile',
+    'DirExists',
+    'FileSize',
+    'FlushFile',
+    'RemoveDir',
+    'CreateDirectory',
+    'GetFileTime',
+    'LogToOpenFile',
+    'LogToOpenFileEx',
+    'PbReadInt',
+    'PbReadFloat',
+    'PbReadBool',
+    'PbReadString',
+    'PbReadColor',
+    'PbReadAngle',
+    'PbReadVector',
+    'PbReadVector2D',
+    'PbGetRepeatedFieldCount',
+    'PbSetInt',
+    'PbSetFloat',
+    'PbSetBool',
+    'PbSetString',
+    'PbSetColor',
+    'PbSetAngle',
+    'PbSetVector',
+    'PbSetVector2D',
+    'PbAddInt',
+    'PbAddFloat',
+    'PbAddBool',
+    'PbAddString',
+    'PbAddColor',
+    'PbAddAngle',
+    'PbAddVector',
+    'PbAddVector2D',
+    'PbRemoveRepeatedFieldValue',
+    'PbReadMessage',
+    'PbReadRepeatedMessage',
+    'PbAddMessage',
+    'SetNextMap',
+    'GetNextMap',
+    'ForceChangeLevel',
+    'GetMapHistorySize',
+    'GetMapHistory',
+    'GeoipCode2',
+    'GeoipCode3',
+    'GeoipCountry',
+    'MarkNativeAsOptional',
+    'RegClientCookie',
+    'FindClientCookie',
+    'SetClientCookie',
+    'GetClientCookie',
+    'SetAuthIdCookie',
+    'AreClientCookiesCached',
+    'OnClientCookiesCached',
+    'CookieMenuHandler',
+    'SetCookiePrefabMenu',
+    'SetCookieMenuItem',
+    'ShowCookieMenu',
+    'GetCookieIterator',
+    'ReadCookieIterator',
+    'GetCookieAccess',
+    'GetClientCookieTime',
+    'LoadTranslations',
+    'SetGlobalTransTarget',
+    'GetClientLanguage',
+    'GetServerLanguage',
+    'GetLanguageCount',
+    'GetLanguageInfo',
+    'SetClientLanguage',
+    'GetLanguageByCode',
+    'GetLanguageByName',
+    'CS_OnBuyCommand',
+    'CS_OnCSWeaponDrop',
+    'CS_OnGetWeaponPrice',
+    'CS_OnTerminateRound',
+    'CS_RespawnPlayer',
+    'CS_SwitchTeam',
+    'CS_DropWeapon',
+    'CS_TerminateRound',
+    'CS_GetTranslatedWeaponAlias',
+    'CS_GetWeaponPrice',
+    'CS_GetClientClanTag',
+    'CS_SetClientClanTag',
+    'CS_GetTeamScore',
+    'CS_SetTeamScore',
+    'CS_GetMVPCount',
+    'CS_SetMVPCount',
+    'CS_GetClientContributionScore',
+    'CS_SetClientContributionScore',
+    'CS_GetClientAssists',
+    'CS_SetClientAssists',
+    'CS_AliasToWeaponID',
+    'CS_WeaponIDToAlias',
+    'CS_IsValidWeaponID',
+    'CS_UpdateClientModel',
+    'LogToGame',
+    'SetRandomSeed',
+    'GetRandomFloat',
+    'GetRandomInt',
+    'IsMapValid',
+    'IsDedicatedServer',
+    'GetEngineTime',
+    'GetGameTime',
+    'GetGameTickCount',
+    'GetGameDescription',
+    'GetGameFolderName',
+    'GetCurrentMap',
+    'PrecacheModel',
+    'PrecacheSentenceFile',
+    'PrecacheDecal',
+    'PrecacheGeneric',
+    'IsModelPrecached',
+    'IsDecalPrecached',
+    'IsGenericPrecached',
+    'PrecacheSound',
+    'IsSoundPrecached',
+    'CreateDialog',
+    'GetEngineVersion',
+    'PrintToChat',
+    'PrintToChatAll',
+    'PrintCenterText',
+    'PrintCenterTextAll',
+    'PrintHintText',
+    'PrintHintTextToAll',
+    'ShowVGUIPanel',
+    'CreateHudSynchronizer',
+    'SetHudTextParams',
+    'SetHudTextParamsEx',
+    'ShowSyncHudText',
+    'ClearSyncHud',
+    'ShowHudText',
+    'ShowMOTDPanel',
+    'DisplayAskConnectBox',
+    'EntIndexToEntRef',
+    'EntRefToEntIndex',
+    'MakeCompatEntRef',
+    'SetClientViewEntity',
+    'SetLightStyle',
+    'GetClientEyePosition',
+    'CreateDataPack',
+    'WritePackCell',
+    'WritePackFloat',
+    'WritePackString',
+    'ReadPackCell',
+    'ReadPackFloat',
+    'ReadPackString',
+    'ResetPack',
+    'GetPackPosition',
+    'SetPackPosition',
+    'IsPackReadable',
+    'LogMessage',
+    'LogToFile',
+    'LogToFileEx',
+    'LogAction',
+    'LogError',
+    'OnLogAction',
+    'GameLogHook',
+    'AddGameLogHook',
+    'RemoveGameLogHook',
+    'FindTeamByName',
+    'StartPrepSDKCall',
+    'PrepSDKCall_SetVirtual',
+    'PrepSDKCall_SetSignature',
+    'PrepSDKCall_SetAddress',
+    'PrepSDKCall_SetFromConf',
+    'PrepSDKCall_SetReturnInfo',
+    'PrepSDKCall_AddParameter',
+    'EndPrepSDKCall',
+    'SDKCall',
+    'GetPlayerResourceEntity',
+)
+
+
+if __name__ == '__main__':  # pragma: no cover
+    import re
+    from urllib.request import FancyURLopener
+
+    from pygments.util import format_lines
+
+    class Opener(FancyURLopener):
+        version = 'Mozilla/5.0 (Pygments Sourcemod Builtins Update)'
+
+    opener = Opener()
+
+    def get_version():
+        f = opener.open('http://docs.sourcemod.net/api/index.php')
+        r = re.compile(r'SourceMod v\.<b>([\d\.]+(?:-\w+)?)</td>')
+        for line in f:
+            m = r.search(line.decode())
+            if m is not None:
+                return m.groups()[0]
+        raise ValueError('No version in api docs')
+
+    def get_sm_functions():
+        f = opener.open('http://docs.sourcemod.net/api/SMfuncs.js')
+        r = re.compile(r'SMfunctions\[\d+\] = Array \("(?:public )?([^,]+)",".+"\);')
+        functions = []
+        for line in f:
+            m = r.match(line.decode())
+            if m is not None:
+                functions.append(m.groups()[0])
+        return functions
+
+    def regenerate(filename, natives):
+        with open(filename, encoding='utf-8') as fp:
+            content = fp.read()
+
+        header = content[:content.find('FUNCTIONS = (')]
+        footer = content[content.find("if __name__ == '__main__':")-1:]
+
+
+        with open(filename, 'w', encoding='utf-8') as fp:
+            fp.write(header)
+            fp.write(format_lines('FUNCTIONS', natives))
+            fp.write('\n\n' + footer)
+
+    def run():
+        version = get_version()
+        print(f'> Downloading function index for SourceMod {version}')
+        functions = get_sm_functions()
+        print('> %d functions found:' % len(functions))
+
+        functionlist = []
+        for full_function_name in functions:
+            print(f'>> {full_function_name}')
+            functionlist.append(full_function_name)
+
+        regenerate(__file__, functionlist)
+
+
+    run()

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/ambient.py

@@ -0,0 +1,75 @@
+"""
+    pygments.lexers.ambient
+    ~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for AmbientTalk language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, include, words, bygroups
+from pygments.token import Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Whitespace
+
+__all__ = ['AmbientTalkLexer']
+
+
+class AmbientTalkLexer(RegexLexer):
+    """
+    Lexer for AmbientTalk source code.
+    """
+    name = 'AmbientTalk'
+    url = 'https://code.google.com/p/ambienttalk'
+    filenames = ['*.at']
+    aliases = ['ambienttalk', 'ambienttalk/2', 'at']
+    mimetypes = ['text/x-ambienttalk']
+    version_added = '2.0'
+
+    flags = re.MULTILINE | re.DOTALL
+
+    builtin = words(('if:', 'then:', 'else:', 'when:', 'whenever:', 'discovered:',
+                     'disconnected:', 'reconnected:', 'takenOffline:', 'becomes:',
+                     'export:', 'as:', 'object:', 'actor:', 'mirror:', 'taggedAs:',
+                     'mirroredBy:', 'is:'))
+    tokens = {
+        'root': [
+            (r'\s+', Whitespace),
+            (r'//.*?\n', Comment.Single),
+            (r'/\*.*?\*/', Comment.Multiline),
+            (r'(def|deftype|import|alias|exclude)\b', Keyword),
+            (builtin, Name.Builtin),
+            (r'(true|false|nil)\b', Keyword.Constant),
+            (r'(~|lobby|jlobby|/)\.', Keyword.Constant, 'namespace'),
+            (r'"(\\\\|\\[^\\]|[^"\\])*"', String),
+            (r'\|', Punctuation, 'arglist'),
+            (r'<:|[*^!%&<>+=,./?-]|:=', Operator),
+            (r"`[a-zA-Z_]\w*", String.Symbol),
+            (r"[a-zA-Z_]\w*:", Name.Function),
+            (r"[{}()\[\];`]", Punctuation),
+            (r'(self|super)\b', Name.Variable.Instance),
+            (r"[a-zA-Z_]\w*", Name.Variable),
+            (r"@[a-zA-Z_]\w*", Name.Class),
+            (r"@\[", Name.Class, 'annotations'),
+            include('numbers'),
+        ],
+        'numbers': [
+            (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float),
+            (r'\d+', Number.Integer)
+        ],
+        'namespace': [
+            (r'[a-zA-Z_]\w*\.', Name.Namespace),
+            (r'[a-zA-Z_]\w*:', Name.Function, '#pop'),
+            (r'[a-zA-Z_]\w*(?!\.)', Name.Function, '#pop')
+        ],
+        'annotations': [
+            (r"(.*?)\]", Name.Class, '#pop')
+        ],
+        'arglist': [
+            (r'\|', Punctuation, '#pop'),
+            (r'(\s*)(,)(\s*)', bygroups(Whitespace, Punctuation, Whitespace)),
+            (r'[a-zA-Z_]\w*', Name.Variable),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/crystal.py

@@ -0,0 +1,364 @@
+"""
+    pygments.lexers.crystal
+    ~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for Crystal.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import ExtendedRegexLexer, include, bygroups, default, \
+    words, line_re
+from pygments.token import Comment, Operator, Keyword, Name, String, Number, \
+    Punctuation, Error, Whitespace
+
+__all__ = ['CrystalLexer']
+
+
+CRYSTAL_OPERATORS = [
+    '!=', '!~', '!', '%', '&&', '&', '**', '*', '+', '-', '/', '<=>', '<<', '<=', '<',
+    '===', '==', '=~', '=', '>=', '>>', '>', '[]=', '[]?', '[]', '^', '||', '|', '~'
+]
+
+
+class CrystalLexer(ExtendedRegexLexer):
+    """
+    For Crystal source code.
+    """
+
+    name = 'Crystal'
+    url = 'https://crystal-lang.org'
+    aliases = ['cr', 'crystal']
+    filenames = ['*.cr']
+    mimetypes = ['text/x-crystal']
+    version_added = '2.2'
+
+    flags = re.DOTALL | re.MULTILINE
+
+    def heredoc_callback(self, match, ctx):
+        # okay, this is the hardest part of parsing Crystal...
+        # match: 1 = <<-?, 2 = quote? 3 = name 4 = quote? 5 = rest of line
+
+        start = match.start(1)
+        yield start, Operator, match.group(1)        # <<-?
+        yield match.start(2), String.Heredoc, match.group(2)    # quote ", ', `
+        yield match.start(3), String.Delimiter, match.group(3)  # heredoc name
+        yield match.start(4), String.Heredoc, match.group(4)    # quote again
+
+        heredocstack = ctx.__dict__.setdefault('heredocstack', [])
+        outermost = not bool(heredocstack)
+        heredocstack.append((match.group(1) == '<<-', match.group(3)))
+
+        ctx.pos = match.start(5)
+        ctx.end = match.end(5)
+        # this may find other heredocs, so limit the recursion depth
+        if len(heredocstack) < 100:
+            yield from self.get_tokens_unprocessed(context=ctx)
+        else:
+            yield ctx.pos, String.Heredoc, match.group(5)
+        ctx.pos = match.end()
+
+        if outermost:
+            # this is the outer heredoc again, now we can process them all
+            for tolerant, hdname in heredocstack:
+                lines = []
+                for match in line_re.finditer(ctx.text, ctx.pos):
+                    if tolerant:
+                        check = match.group().strip()
+                    else:
+                        check = match.group().rstrip()
+                    if check == hdname:
+                        for amatch in lines:
+                            yield amatch.start(), String.Heredoc, amatch.group()
+                        yield match.start(), String.Delimiter, match.group()
+                        ctx.pos = match.end()
+                        break
+                    else:
+                        lines.append(match)
+                else:
+                    # end of heredoc not found -- error!
+                    for amatch in lines:
+                        yield amatch.start(), Error, amatch.group()
+            ctx.end = len(ctx.text)
+            del heredocstack[:]
+
+    def gen_crystalstrings_rules():
+        states = {}
+        states['strings'] = [
+            (r'\:\w+[!?]?', String.Symbol),
+            (words(CRYSTAL_OPERATORS, prefix=r'\:'), String.Symbol),
+            (r":'(\\\\|\\[^\\]|[^'\\])*'", String.Symbol),
+            # This allows arbitrary text after '\ for simplicity
+            (r"'(\\\\|\\'|[^']|\\[^'\\]+)'", String.Char),
+            (r':"', String.Symbol, 'simple-sym'),
+            # Crystal doesn't have "symbol:"s but this simplifies function args
+            (r'([a-zA-Z_]\w*)(:)(?!:)', bygroups(String.Symbol, Punctuation)),
+            (r'"', String.Double, 'simple-string'),
+            (r'(?<!\.)`', String.Backtick, 'simple-backtick'),
+        ]
+
+        # double-quoted string and symbol
+        for name, ttype, end in ('string', String.Double, '"'), \
+                                ('sym', String.Symbol, '"'), \
+                                ('backtick', String.Backtick, '`'):
+            states['simple-'+name] = [
+                include('string-escaped' if name == 'sym' else 'string-intp-escaped'),
+                (rf'[^\\{end}#]+', ttype),
+                (r'[\\#]', ttype),
+                (end, ttype, '#pop'),
+            ]
+
+        # https://crystal-lang.org/docs/syntax_and_semantics/literals/string.html#percent-string-literals
+        for lbrace, rbrace, bracecc, name in \
+                ('\\{', '\\}', '{}', 'cb'), \
+                ('\\[', '\\]', '\\[\\]', 'sb'), \
+                ('\\(', '\\)', '()', 'pa'), \
+                ('<', '>', '<>', 'ab'), \
+                ('\\|', '\\|', '\\|', 'pi'):
+            states[name+'-intp-string'] = [
+                (r'\\' + lbrace, String.Other),
+            ] + (lbrace != rbrace) * [
+                (lbrace, String.Other, '#push'),
+            ] + [
+                (rbrace, String.Other, '#pop'),
+                include('string-intp-escaped'),
+                (r'[\\#' + bracecc + ']', String.Other),
+                (r'[^\\#' + bracecc + ']+', String.Other),
+            ]
+            states['strings'].append((r'%Q?' + lbrace, String.Other,
+                                      name+'-intp-string'))
+            states[name+'-string'] = [
+                (r'\\[\\' + bracecc + ']', String.Other),
+            ] + (lbrace != rbrace) * [
+                (lbrace, String.Other, '#push'),
+            ] + [
+                (rbrace, String.Other, '#pop'),
+                (r'[\\#' + bracecc + ']', String.Other),
+                (r'[^\\#' + bracecc + ']+', String.Other),
+            ]
+            # https://crystal-lang.org/docs/syntax_and_semantics/literals/array.html#percent-array-literals
+            states['strings'].append((r'%[qwi]' + lbrace, String.Other,
+                                      name+'-string'))
+            states[name+'-regex'] = [
+                (r'\\[\\' + bracecc + ']', String.Regex),
+            ] + (lbrace != rbrace) * [
+                (lbrace, String.Regex, '#push'),
+            ] + [
+                (rbrace + '[imsx]*', String.Regex, '#pop'),
+                include('string-intp'),
+                (r'[\\#' + bracecc + ']', String.Regex),
+                (r'[^\\#' + bracecc + ']+', String.Regex),
+            ]
+            states['strings'].append((r'%r' + lbrace, String.Regex,
+                                      name+'-regex'))
+
+        return states
+
+    tokens = {
+        'root': [
+            (r'#.*?$', Comment.Single),
+            # keywords
+            (words('''
+                abstract asm begin break case do else elsif end ensure extend if in
+                include next of private protected require rescue return select self super
+                then unless until when while with yield
+            '''.split(), suffix=r'\b'), Keyword),
+            (words('''
+                previous_def forall out uninitialized __DIR__ __FILE__ __LINE__
+                __END_LINE__
+            '''.split(), prefix=r'(?<!\.)', suffix=r'\b'), Keyword.Pseudo),
+            # https://crystal-lang.org/docs/syntax_and_semantics/is_a.html
+            (r'\.(is_a\?|nil\?|responds_to\?|as\?|as\b)', Keyword.Pseudo),
+            (words(['true', 'false', 'nil'], suffix=r'\b'), Keyword.Constant),
+            # start of function, class and module names
+            (r'(module|lib)(\s+)([a-zA-Z_]\w*(?:::[a-zA-Z_]\w*)*)',
+             bygroups(Keyword, Whitespace, Name.Namespace)),
+            (r'(def|fun|macro)(\s+)((?:[a-zA-Z_]\w*::)*)',
+             bygroups(Keyword, Whitespace, Name.Namespace), 'funcname'),
+            (r'def(?=[*%&^`~+-/\[<>=])', Keyword, 'funcname'),
+            (r'(annotation|class|struct|union|type|alias|enum)(\s+)((?:[a-zA-Z_]\w*::)*)',
+             bygroups(Keyword, Whitespace, Name.Namespace), 'classname'),
+            # https://crystal-lang.org/api/toplevel.html
+            (words('''
+                instance_sizeof offsetof pointerof sizeof typeof
+            '''.split(), prefix=r'(?<!\.)', suffix=r'\b'), Keyword.Pseudo),
+            # macros
+            (r'(?<!\.)(debugger\b|p!|pp!|record\b|spawn\b)', Name.Builtin.Pseudo),
+            # builtins
+            (words('''
+                abort at_exit caller exit gets loop main p pp print printf puts
+                raise rand read_line sleep spawn sprintf system
+            '''.split(), prefix=r'(?<!\.)', suffix=r'\b'), Name.Builtin),
+            # https://crystal-lang.org/api/Object.html#macro-summary
+            (r'(?<!\.)(((class_)?((getter|property)\b[!?]?|setter\b))|'
+             r'(def_(clone|equals|equals_and_hash|hash)|delegate|forward_missing_to)\b)',
+             Name.Builtin.Pseudo),
+            # normal heredocs
+            (r'(?<!\w)(<<-?)(["`\']?)([a-zA-Z_]\w*)(\2)(.*?\n)',
+             heredoc_callback),
+            # empty string heredocs
+            (r'(<<-?)("|\')()(\2)(.*?\n)', heredoc_callback),
+            (r'__END__', Comment.Preproc, 'end-part'),
+            # multiline regex (after keywords or assignments)
+            (r'(?:^|(?<=[=<>~!:])|'
+             r'(?<=(?:\s|;)when\s)|'
+             r'(?<=(?:\s|;)or\s)|'
+             r'(?<=(?:\s|;)and\s)|'
+             r'(?<=\.index\s)|'
+             r'(?<=\.scan\s)|'
+             r'(?<=\.sub\s)|'
+             r'(?<=\.sub!\s)|'
+             r'(?<=\.gsub\s)|'
+             r'(?<=\.gsub!\s)|'
+             r'(?<=\.match\s)|'
+             r'(?<=(?:\s|;)if\s)|'
+             r'(?<=(?:\s|;)elsif\s)|'
+             r'(?<=^when\s)|'
+             r'(?<=^index\s)|'
+             r'(?<=^scan\s)|'
+             r'(?<=^sub\s)|'
+             r'(?<=^gsub\s)|'
+             r'(?<=^sub!\s)|'
+             r'(?<=^gsub!\s)|'
+             r'(?<=^match\s)|'
+             r'(?<=^if\s)|'
+             r'(?<=^elsif\s)'
+             r')(\s*)(/)', bygroups(Whitespace, String.Regex), 'multiline-regex'),
+            # multiline regex (in method calls or subscripts)
+            (r'(?<=\(|,|\[)/', String.Regex, 'multiline-regex'),
+            # multiline regex (this time the funny no whitespace rule)
+            (r'(\s+)(/)(?![\s=])', bygroups(Whitespace, String.Regex),
+             'multiline-regex'),
+            # lex numbers and ignore following regular expressions which
+            # are division operators in fact (grrrr. i hate that. any
+            # better ideas?)
+            # since pygments 0.7 we also eat a "?" operator after numbers
+            # so that the char operator does not work. Chars are not allowed
+            # there so that you can use the ternary operator.
+            # stupid example:
+            #   x>=0?n[x]:""
+            (r'(0o[0-7]+(?:_[0-7]+)*(?:_?[iu][0-9]+)?)\b(\s*)([/?])?',
+             bygroups(Number.Oct, Whitespace, Operator)),
+            (r'(0x[0-9A-Fa-f]+(?:_[0-9A-Fa-f]+)*(?:_?[iu][0-9]+)?)\b(\s*)([/?])?',
+             bygroups(Number.Hex, Whitespace, Operator)),
+            (r'(0b[01]+(?:_[01]+)*(?:_?[iu][0-9]+)?)\b(\s*)([/?])?',
+             bygroups(Number.Bin, Whitespace, Operator)),
+            # 3 separate expressions for floats because any of the 3 optional
+            # parts makes it a float
+            (r'((?:0(?![0-9])|[1-9][\d_]*)(?:\.\d[\d_]*)(?:e[+-]?[0-9]+)?'
+             r'(?:_?f[0-9]+)?)(\s*)([/?])?',
+             bygroups(Number.Float, Whitespace, Operator)),
+            (r'((?:0(?![0-9])|[1-9][\d_]*)(?:\.\d[\d_]*)?(?:e[+-]?[0-9]+)'
+             r'(?:_?f[0-9]+)?)(\s*)([/?])?',
+             bygroups(Number.Float, Whitespace, Operator)),
+            (r'((?:0(?![0-9])|[1-9][\d_]*)(?:\.\d[\d_]*)?(?:e[+-]?[0-9]+)?'
+             r'(?:_?f[0-9]+))(\s*)([/?])?',
+             bygroups(Number.Float, Whitespace, Operator)),
+            (r'(0\b|[1-9][\d]*(?:_\d+)*(?:_?[iu][0-9]+)?)\b(\s*)([/?])?',
+             bygroups(Number.Integer, Whitespace, Operator)),
+            # Names
+            (r'@@[a-zA-Z_]\w*', Name.Variable.Class),
+            (r'@[a-zA-Z_]\w*', Name.Variable.Instance),
+            (r'\$\w+', Name.Variable.Global),
+            (r'\$[!@&`\'+~=/\\,;.<>_*$?:"^-]', Name.Variable.Global),
+            (r'\$-[0adFiIlpvw]', Name.Variable.Global),
+            (r'::', Operator),
+            include('strings'),
+            # https://crystal-lang.org/reference/syntax_and_semantics/literals/char.html
+            (r'\?(\\[MC]-)*'  # modifiers
+             r'(\\([\\abefnrtv#"\']|[0-7]{1,3}|x[a-fA-F0-9]{2}|u[a-fA-F0-9]{4}|u\{[a-fA-F0-9 ]+\})|\S)'
+             r'(?!\w)',
+             String.Char),
+            (r'[A-Z][A-Z_]+\b(?!::|\.)', Name.Constant),
+            # macro expansion
+            (r'\{%', String.Interpol, 'in-macro-control'),
+            (r'\{\{', String.Interpol, 'in-macro-expr'),
+            # annotations
+            (r'(@\[)(\s*)([A-Z]\w*(::[A-Z]\w*)*)',
+             bygroups(Operator, Whitespace, Name.Decorator), 'in-annot'),
+            # this is needed because Crystal attributes can look
+            # like keywords (class) or like this: ` ?!?
+            (words(CRYSTAL_OPERATORS, prefix=r'(\.|::)'),
+             bygroups(Operator, Name.Operator)),
+            (r'(\.|::)([a-zA-Z_]\w*[!?]?|[*%&^`~+\-/\[<>=])',
+             bygroups(Operator, Name)),
+            # Names can end with [!?] unless it's "!="
+            (r'[a-zA-Z_]\w*(?:[!?](?!=))?', Name),
+            (r'(\[|\]\??|\*\*|<=>?|>=|<<?|>>?|=~|===|'
+             r'!~|&&?|\|\||\.{1,3})', Operator),
+            (r'[-+/*%=<>&!^|~]=?', Operator),
+            (r'[(){};,/?:\\]', Punctuation),
+            (r'\s+', Whitespace)
+        ],
+        'funcname': [
+            (r'(?:([a-zA-Z_]\w*)(\.))?'
+             r'([a-zA-Z_]\w*[!?]?|\*\*?|[-+]@?|'
+             r'[/%&|^`~]|\[\]=?|<<|>>|<=?>|>=?|===?)',
+             bygroups(Name.Class, Operator, Name.Function), '#pop'),
+            default('#pop')
+        ],
+        'classname': [
+            (r'[A-Z_]\w*', Name.Class),
+            (r'(\()(\s*)([A-Z_]\w*)(\s*)(\))',
+             bygroups(Punctuation, Whitespace, Name.Class, Whitespace, Punctuation)),
+            default('#pop')
+        ],
+        'in-intp': [
+            (r'\{', String.Interpol, '#push'),
+            (r'\}', String.Interpol, '#pop'),
+            include('root'),
+        ],
+        'string-intp': [
+            (r'#\{', String.Interpol, 'in-intp'),
+        ],
+        'string-escaped': [
+            # https://crystal-lang.org/reference/syntax_and_semantics/literals/string.html
+            (r'\\([\\abefnrtv#"\']|[0-7]{1,3}|x[a-fA-F0-9]{2}|u[a-fA-F0-9]{4}|u\{[a-fA-F0-9 ]+\})',
+             String.Escape)
+        ],
+        'string-intp-escaped': [
+            include('string-intp'),
+            include('string-escaped'),
+        ],
+        'interpolated-regex': [
+            include('string-intp'),
+            (r'[\\#]', String.Regex),
+            (r'[^\\#]+', String.Regex),
+        ],
+        'interpolated-string': [
+            include('string-intp'),
+            (r'[\\#]', String.Other),
+            (r'[^\\#]+', String.Other),
+        ],
+        'multiline-regex': [
+            include('string-intp'),
+            (r'\\\\', String.Regex),
+            (r'\\/', String.Regex),
+            (r'[\\#]', String.Regex),
+            (r'[^\\/#]+', String.Regex),
+            (r'/[imsx]*', String.Regex, '#pop'),
+        ],
+        'end-part': [
+            (r'.+', Comment.Preproc, '#pop')
+        ],
+        'in-macro-control': [
+            (r'\{%', String.Interpol, '#push'),
+            (r'%\}', String.Interpol, '#pop'),
+            (r'(for|verbatim)\b', Keyword),
+            include('root'),
+        ],
+        'in-macro-expr': [
+            (r'\{\{', String.Interpol, '#push'),
+            (r'\}\}', String.Interpol, '#pop'),
+            include('root'),
+        ],
+        'in-annot': [
+            (r'\[', Operator, '#push'),
+            (r'\]', Operator, '#pop'),
+            include('root'),
+        ],
+    }
+    tokens.update(gen_crystalstrings_rules())

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/dsls.py

@@ -0,0 +1,970 @@
+"""
+    pygments.lexers.dsls
+    ~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for various domain-specific languages.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import ExtendedRegexLexer, RegexLexer, bygroups, words, \
+    include, default, this, using, combined
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Whitespace
+
+__all__ = ['ProtoBufLexer', 'ZeekLexer', 'PuppetLexer', 'RslLexer',
+           'MscgenLexer', 'VGLLexer', 'AlloyLexer', 'PanLexer',
+           'CrmshLexer', 'ThriftLexer', 'FlatlineLexer', 'SnowballLexer']
+
+
+class ProtoBufLexer(RegexLexer):
+    """
+    Lexer for Protocol Buffer definition files.
+    """
+
+    name = 'Protocol Buffer'
+    url = 'https://developers.google.com/protocol-buffers/'
+    aliases = ['protobuf', 'proto']
+    filenames = ['*.proto']
+    version_added = '1.4'
+
+    tokens = {
+        'root': [
+            (r'[ \t]+', Whitespace),
+            (r'[,;{}\[\]()<>]', Punctuation),
+            (r'/(\\\n)?/(\n|(.|\n)*?[^\\]\n)', Comment.Single),
+            (r'/(\\\n)?\*(.|\n)*?\*(\\\n)?/', Comment.Multiline),
+            (words((
+                'import', 'option', 'optional', 'required', 'repeated',
+                'reserved', 'default', 'packed', 'ctype', 'extensions', 'to',
+                'max', 'rpc', 'returns', 'oneof', 'syntax'), prefix=r'\b', suffix=r'\b'),
+             Keyword),
+            (words((
+                'int32', 'int64', 'uint32', 'uint64', 'sint32', 'sint64',
+                'fixed32', 'fixed64', 'sfixed32', 'sfixed64',
+                'float', 'double', 'bool', 'string', 'bytes'), suffix=r'\b'),
+             Keyword.Type),
+            (r'(true|false)\b', Keyword.Constant),
+            (r'(package)(\s+)', bygroups(Keyword.Namespace, Whitespace), 'package'),
+            (r'(message|extend)(\s+)',
+             bygroups(Keyword.Declaration, Whitespace), 'message'),
+            (r'(enum|group|service)(\s+)',
+             bygroups(Keyword.Declaration, Whitespace), 'type'),
+            (r'\".*?\"', String),
+            (r'\'.*?\'', String),
+            (r'(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+[LlUu]*', Number.Float),
+            (r'(\d+\.\d*|\.\d+|\d+[fF])[fF]?', Number.Float),
+            (r'(\-?(inf|nan))\b', Number.Float),
+            (r'0x[0-9a-fA-F]+[LlUu]*', Number.Hex),
+            (r'0[0-7]+[LlUu]*', Number.Oct),
+            (r'\d+[LlUu]*', Number.Integer),
+            (r'[+-=]', Operator),
+            (r'([a-zA-Z_][\w.]*)([ \t]*)(=)',
+             bygroups(Name.Attribute, Whitespace, Operator)),
+            (r'[a-zA-Z_][\w.]*', Name),
+        ],
+        'package': [
+            (r'[a-zA-Z_][\w\.]*', Name.Namespace, '#pop'),
+            default('#pop'),
+        ],
+        'message': [
+            (r'[a-zA-Z_]\w*', Name.Class, '#pop'),
+            default('#pop'),
+        ],
+        'type': [
+            (r'[a-zA-Z_]\w*', Name, '#pop'),
+            default('#pop'),
+        ],
+    }
+
+
+class ThriftLexer(RegexLexer):
+    """
+    For Thrift interface definitions.
+    """
+    name = 'Thrift'
+    url = 'https://thrift.apache.org/'
+    aliases = ['thrift']
+    filenames = ['*.thrift']
+    mimetypes = ['application/x-thrift']
+    version_added = '2.1'
+
+    tokens = {
+        'root': [
+            include('whitespace'),
+            include('comments'),
+            (r'"', String.Double, combined('stringescape', 'dqs')),
+            (r'\'', String.Single, combined('stringescape', 'sqs')),
+            (r'(namespace)(\s+)',
+                bygroups(Keyword.Namespace, Whitespace), 'namespace'),
+            (r'(enum|union|struct|service|exception)(\s+)',
+                bygroups(Keyword.Declaration, Whitespace), 'class'),
+            (r'((?:(?:[^\W\d]|\$)[\w.\[\]$<>]*\s+)+?)'  # return arguments
+             r'((?:[^\W\d]|\$)[\w$]*)'                  # method name
+             r'(\s*)(\()',                              # signature start
+             bygroups(using(this), Name.Function, Whitespace, Operator)),
+            include('keywords'),
+            include('numbers'),
+            (r'[&=]', Operator),
+            (r'[:;,{}()<>\[\]]', Punctuation),
+            (r'[a-zA-Z_](\.\w|\w)*', Name),
+        ],
+        'whitespace': [
+            (r'\n', Whitespace),
+            (r'\s+', Whitespace),
+        ],
+        'comments': [
+            (r'#.*$', Comment),
+            (r'//.*?\n', Comment),
+            (r'/\*[\w\W]*?\*/', Comment.Multiline),
+        ],
+        'stringescape': [
+            (r'\\([\\nrt"\'])', String.Escape),
+        ],
+        'dqs': [
+            (r'"', String.Double, '#pop'),
+            (r'[^\\"\n]+', String.Double),
+        ],
+        'sqs': [
+            (r"'", String.Single, '#pop'),
+            (r'[^\\\'\n]+', String.Single),
+        ],
+        'namespace': [
+            (r'[a-z*](\.\w|\w)*', Name.Namespace, '#pop'),
+            default('#pop'),
+        ],
+        'class': [
+            (r'[a-zA-Z_]\w*', Name.Class, '#pop'),
+            default('#pop'),
+        ],
+        'keywords': [
+            (r'(async|oneway|extends|throws|required|optional)\b', Keyword),
+            (r'(true|false)\b', Keyword.Constant),
+            (r'(const|typedef)\b', Keyword.Declaration),
+            (words((
+                'cpp_namespace', 'cpp_include', 'cpp_type', 'java_package',
+                'cocoa_prefix', 'csharp_namespace', 'delphi_namespace',
+                'php_namespace', 'py_module', 'perl_package',
+                'ruby_namespace', 'smalltalk_category', 'smalltalk_prefix',
+                'xsd_all', 'xsd_optional', 'xsd_nillable', 'xsd_namespace',
+                'xsd_attrs', 'include'), suffix=r'\b'),
+             Keyword.Namespace),
+            (words((
+                'void', 'bool', 'byte', 'i16', 'i32', 'i64', 'double',
+                'string', 'binary', 'map', 'list', 'set', 'slist',
+                'senum'), suffix=r'\b'),
+             Keyword.Type),
+            (words((
+                'BEGIN', 'END', '__CLASS__', '__DIR__', '__FILE__',
+                '__FUNCTION__', '__LINE__', '__METHOD__', '__NAMESPACE__',
+                'abstract', 'alias', 'and', 'args', 'as', 'assert', 'begin',
+                'break', 'case', 'catch', 'class', 'clone', 'continue',
+                'declare', 'def', 'default', 'del', 'delete', 'do', 'dynamic',
+                'elif', 'else', 'elseif', 'elsif', 'end', 'enddeclare',
+                'endfor', 'endforeach', 'endif', 'endswitch', 'endwhile',
+                'ensure', 'except', 'exec', 'finally', 'float', 'for',
+                'foreach', 'function', 'global', 'goto', 'if', 'implements',
+                'import', 'in', 'inline', 'instanceof', 'interface', 'is',
+                'lambda', 'module', 'native', 'new', 'next', 'nil', 'not',
+                'or', 'pass', 'public', 'print', 'private', 'protected',
+                'raise', 'redo', 'rescue', 'retry', 'register', 'return',
+                'self', 'sizeof', 'static', 'super', 'switch', 'synchronized',
+                'then', 'this', 'throw', 'transient', 'try', 'undef',
+                'unless', 'unsigned', 'until', 'use', 'var', 'virtual',
+                'volatile', 'when', 'while', 'with', 'xor', 'yield'),
+                prefix=r'\b', suffix=r'\b'),
+             Keyword.Reserved),
+        ],
+        'numbers': [
+            (r'[+-]?(\d+\.\d+([eE][+-]?\d+)?|\.?\d+[eE][+-]?\d+)', Number.Float),
+            (r'[+-]?0x[0-9A-Fa-f]+', Number.Hex),
+            (r'[+-]?[0-9]+', Number.Integer),
+        ],
+    }
+
+
+class ZeekLexer(RegexLexer):
+    """
+    For Zeek scripts.
+    """
+    name = 'Zeek'
+    url = 'https://www.zeek.org/'
+    aliases = ['zeek', 'bro']
+    filenames = ['*.zeek', '*.bro']
+    version_added = '2.5'
+
+    _hex = r'[0-9a-fA-F]'
+    _float = r'((\d*\.?\d+)|(\d+\.?\d*))([eE][-+]?\d+)?'
+    _h = r'[A-Za-z0-9][-A-Za-z0-9]*'
+
+    tokens = {
+        'root': [
+            include('whitespace'),
+            include('comments'),
+            include('directives'),
+            include('attributes'),
+            include('types'),
+            include('keywords'),
+            include('literals'),
+            include('operators'),
+            include('punctuation'),
+            (r'((?:[A-Za-z_]\w*)(?:::(?:[A-Za-z_]\w*))*)(?=\s*\()',
+                Name.Function),
+            include('identifiers'),
+        ],
+
+        'whitespace': [
+            (r'\n', Whitespace),
+            (r'\s+', Whitespace),
+            (r'(\\)(\n)', bygroups(Text, Whitespace)),
+        ],
+
+        'comments': [
+            (r'#.*$', Comment),
+        ],
+
+        'directives': [
+            (r'@(load-plugin|load-sigs|load|unload)\b.*$', Comment.Preproc),
+            (r'@(DEBUG|DIR|FILENAME|deprecated|if|ifdef|ifndef|else|endif)\b', Comment.Preproc),
+            (r'(@prefixes)(\s*)((\+?=).*)$', bygroups(Comment.Preproc,
+                Whitespace, Comment.Preproc)),
+        ],
+
+        'attributes': [
+            (words(('redef', 'priority', 'log', 'optional', 'default', 'add_func',
+                    'delete_func', 'expire_func', 'read_expire', 'write_expire',
+                    'create_expire', 'synchronized', 'persistent', 'rotate_interval',
+                    'rotate_size', 'encrypt', 'raw_output', 'mergeable', 'error_handler',
+                    'type_column', 'deprecated'),
+                prefix=r'&', suffix=r'\b'),
+             Keyword.Pseudo),
+        ],
+
+        'types': [
+            (words(('any',
+                    'enum', 'record', 'set', 'table', 'vector',
+                    'function', 'hook', 'event',
+                    'addr', 'bool', 'count', 'double', 'file', 'int', 'interval',
+                    'pattern', 'port', 'string', 'subnet', 'time'),
+                suffix=r'\b'),
+             Keyword.Type),
+
+            (r'(opaque)(\s+)(of)(\s+)((?:[A-Za-z_]\w*)(?:::(?:[A-Za-z_]\w*))*)\b',
+                bygroups(Keyword.Type, Whitespace, Operator.Word, Whitespace, Keyword.Type)),
+
+            (r'(type)(\s+)((?:[A-Za-z_]\w*)(?:::(?:[A-Za-z_]\w*))*)(\s*)(:)(\s*)\b(record|enum)\b',
+                bygroups(Keyword, Whitespace, Name.Class, Whitespace, Operator, Whitespace, Keyword.Type)),
+
+            (r'(type)(\s+)((?:[A-Za-z_]\w*)(?:::(?:[A-Za-z_]\w*))*)(\s*)(:)',
+                bygroups(Keyword, Whitespace, Name, Whitespace, Operator)),
+
+            (r'(redef)(\s+)(record|enum)(\s+)((?:[A-Za-z_]\w*)(?:::(?:[A-Za-z_]\w*))*)\b',
+                bygroups(Keyword, Whitespace, Keyword.Type, Whitespace, Name.Class)),
+        ],
+
+        'keywords': [
+            (words(('redef', 'export', 'if', 'else', 'for', 'while',
+                    'return', 'break', 'next', 'continue', 'fallthrough',
+                    'switch', 'default', 'case',
+                    'add', 'delete',
+                    'when', 'timeout', 'schedule'),
+                suffix=r'\b'),
+             Keyword),
+            (r'(print)\b', Keyword),
+            (r'(global|local|const|option)\b', Keyword.Declaration),
+            (r'(module)(\s+)(([A-Za-z_]\w*)(?:::([A-Za-z_]\w*))*)\b',
+                bygroups(Keyword.Namespace, Whitespace, Name.Namespace)),
+        ],
+
+        'literals': [
+            (r'"', String, 'string'),
+
+            # Not the greatest match for patterns, but generally helps
+            # disambiguate between start of a pattern and just a division
+            # operator.
+            (r'/(?=.*/)', String.Regex, 'regex'),
+
+            (r'(T|F)\b', Keyword.Constant),
+
+            # Port
+            (r'\d{1,5}/(udp|tcp|icmp|unknown)\b', Number),
+
+            # IPv4 Address
+            (r'(\d{1,3}.){3}(\d{1,3})\b', Number),
+
+            # IPv6 Address
+            (r'\[([0-9a-fA-F]{0,4}:){2,7}([0-9a-fA-F]{0,4})?((\d{1,3}.){3}(\d{1,3}))?\]', Number),
+
+            # Numeric
+            (r'0[xX]' + _hex + r'+\b', Number.Hex),
+            (_float + r'\s*(day|hr|min|sec|msec|usec)s?\b', Number.Float),
+            (_float + r'\b', Number.Float),
+            (r'(\d+)\b', Number.Integer),
+
+            # Hostnames
+            (_h + r'(\.' + _h + r')+', String),
+        ],
+
+        'operators': [
+            (r'[!%*/+<=>~|&^-]', Operator),
+            (r'([-+=&|]{2}|[+=!><-]=)', Operator),
+            (r'(in|as|is|of)\b', Operator.Word),
+            (r'\??\$', Operator),
+        ],
+
+        'punctuation': [
+            (r'[{}()\[\],;.]', Punctuation),
+            # The "ternary if", which uses '?' and ':', could instead be
+            # treated as an Operator, but colons are more frequently used to
+            # separate field/identifier names from their types, so the (often)
+            # less-prominent Punctuation is used even with '?' for consistency.
+            (r'[?:]', Punctuation),
+        ],
+
+        'identifiers': [
+            (r'([a-zA-Z_]\w*)(::)', bygroups(Name, Punctuation)),
+            (r'[a-zA-Z_]\w*', Name)
+        ],
+
+        'string': [
+            (r'\\.', String.Escape),
+            (r'%-?[0-9]*(\.[0-9]+)?[DTd-gsx]', String.Escape),
+            (r'"', String, '#pop'),
+            (r'.', String),
+        ],
+
+        'regex': [
+            (r'\\.', String.Escape),
+            (r'/', String.Regex, '#pop'),
+            (r'.', String.Regex),
+        ],
+    }
+
+
+BroLexer = ZeekLexer
+
+
+class PuppetLexer(RegexLexer):
+    """
+    For Puppet configuration DSL.
+    """
+    name = 'Puppet'
+    url = 'https://puppet.com/'
+    aliases = ['puppet']
+    filenames = ['*.pp']
+    version_added = '1.6'
+
+    tokens = {
+        'root': [
+            include('comments'),
+            include('keywords'),
+            include('names'),
+            include('numbers'),
+            include('operators'),
+            include('strings'),
+
+            (r'[]{}:(),;[]', Punctuation),
+            (r'\s+', Whitespace),
+        ],
+
+        'comments': [
+            (r'(\s*)(#.*)$', bygroups(Whitespace, Comment)),
+            (r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment.Multiline),
+        ],
+
+        'operators': [
+            (r'(=>|\?|<|>|=|\+|-|/|\*|~|!|\|)', Operator),
+            (r'(in|and|or|not)\b', Operator.Word),
+        ],
+
+        'names': [
+            (r'[a-zA-Z_]\w*', Name.Attribute),
+            (r'(\$\S+)(\[)(\S+)(\])', bygroups(Name.Variable, Punctuation,
+                                               String, Punctuation)),
+            (r'\$\S+', Name.Variable),
+        ],
+
+        'numbers': [
+            # Copypasta from the Python lexer
+            (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?j?', Number.Float),
+            (r'\d+[eE][+-]?[0-9]+j?', Number.Float),
+            (r'0[0-7]+j?', Number.Oct),
+            (r'0[xX][a-fA-F0-9]+', Number.Hex),
+            (r'\d+L', Number.Integer.Long),
+            (r'\d+j?', Number.Integer)
+        ],
+
+        'keywords': [
+            # Left out 'group' and 'require'
+            # Since they're often used as attributes
+            (words((
+                'absent', 'alert', 'alias', 'audit', 'augeas', 'before', 'case',
+                'check', 'class', 'computer', 'configured', 'contained',
+                'create_resources', 'crit', 'cron', 'debug', 'default',
+                'define', 'defined', 'directory', 'else', 'elsif', 'emerg',
+                'err', 'exec', 'extlookup', 'fail', 'false', 'file',
+                'filebucket', 'fqdn_rand', 'generate', 'host', 'if', 'import',
+                'include', 'info', 'inherits', 'inline_template', 'installed',
+                'interface', 'k5login', 'latest', 'link', 'loglevel',
+                'macauthorization', 'mailalias', 'maillist', 'mcx', 'md5',
+                'mount', 'mounted', 'nagios_command', 'nagios_contact',
+                'nagios_contactgroup', 'nagios_host', 'nagios_hostdependency',
+                'nagios_hostescalation', 'nagios_hostextinfo', 'nagios_hostgroup',
+                'nagios_service', 'nagios_servicedependency', 'nagios_serviceescalation',
+                'nagios_serviceextinfo', 'nagios_servicegroup', 'nagios_timeperiod',
+                'node', 'noop', 'notice', 'notify', 'package', 'present', 'purged',
+                'realize', 'regsubst', 'resources', 'role', 'router', 'running',
+                'schedule', 'scheduled_task', 'search', 'selboolean', 'selmodule',
+                'service', 'sha1', 'shellquote', 'split', 'sprintf',
+                'ssh_authorized_key', 'sshkey', 'stage', 'stopped', 'subscribe',
+                'tag', 'tagged', 'template', 'tidy', 'true', 'undef', 'unmounted',
+                'user', 'versioncmp', 'vlan', 'warning', 'yumrepo', 'zfs', 'zone',
+                'zpool'), prefix='(?i)', suffix=r'\b'),
+             Keyword),
+        ],
+
+        'strings': [
+            (r'"([^"])*"', String),
+            (r"'(\\'|[^'])*'", String),
+        ],
+
+    }
+
+
+class RslLexer(RegexLexer):
+    """
+    RSL is the formal specification
+    language used in RAISE (Rigorous Approach to Industrial Software Engineering)
+    method.
+    """
+    name = 'RSL'
+    url = 'http://en.wikipedia.org/wiki/RAISE'
+    aliases = ['rsl']
+    filenames = ['*.rsl']
+    mimetypes = ['text/rsl']
+    version_added = '2.0'
+
+    flags = re.MULTILINE | re.DOTALL
+
+    tokens = {
+        'root': [
+            (words((
+                'Bool', 'Char', 'Int', 'Nat', 'Real', 'Text', 'Unit', 'abs',
+                'all', 'always', 'any', 'as', 'axiom', 'card', 'case', 'channel',
+                'chaos', 'class', 'devt_relation', 'dom', 'elems', 'else', 'elif',
+                'end', 'exists', 'extend', 'false', 'for', 'hd', 'hide', 'if',
+                'in', 'is', 'inds', 'initialise', 'int', 'inter', 'isin', 'len',
+                'let', 'local', 'ltl_assertion', 'object', 'of', 'out', 'post',
+                'pre', 'read', 'real', 'rng', 'scheme', 'skip', 'stop', 'swap',
+                'then', 'theory', 'test_case', 'tl', 'transition_system', 'true',
+                'type', 'union', 'until', 'use', 'value', 'variable', 'while',
+                'with', 'write', '~isin', '-inflist', '-infset', '-list',
+                '-set'), prefix=r'\b', suffix=r'\b'),
+             Keyword),
+            (r'(variable|value)\b', Keyword.Declaration),
+            (r'--.*?\n', Comment),
+            (r'<:.*?:>', Comment),
+            (r'\{!.*?!\}', Comment),
+            (r'/\*.*?\*/', Comment),
+            (r'^([ \t]*)([\w]+)([ \t]*)(:[^:])', bygroups(Whitespace,
+                Name.Function, Whitespace, Name.Function)),
+            (r'(^[ \t]*)([\w]+)([ \t]*)(\([\w\s,]*\))([ \t]*)(is|as)',
+             bygroups(Whitespace, Name.Function, Whitespace, Text,
+                 Whitespace, Keyword)),
+            (r'\b[A-Z]\w*\b', Keyword.Type),
+            (r'(true|false)\b', Keyword.Constant),
+            (r'".*"', String),
+            (r'\'.\'', String.Char),
+            (r'(><|->|-m->|/\\|<=|<<=|<\.|\|\||\|\^\||-~->|-~m->|\\/|>=|>>|'
+             r'\.>|\+\+|-\\|<->|=>|:-|~=|\*\*|<<|>>=|\+>|!!|\|=\||#)',
+             Operator),
+            (r'[0-9]+\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
+            (r'0x[0-9a-f]+', Number.Hex),
+            (r'[0-9]+', Number.Integer),
+            (r'\s+', Whitespace),
+            (r'.', Text),
+        ],
+    }
+
+    def analyse_text(text):
+        """
+        Check for the most common text in the beginning of a RSL file.
+        """
+        if re.search(r'scheme\s*.*?=\s*class\s*type', text, re.I) is not None:
+            return 1.0
+
+
+class MscgenLexer(RegexLexer):
+    """
+    For Mscgen files.
+    """
+    name = 'Mscgen'
+    url = 'http://www.mcternan.me.uk/mscgen/'
+    aliases = ['mscgen', 'msc']
+    filenames = ['*.msc']
+    version_added = '1.6'
+
+    _var = r'(\w+|"(?:\\"|[^"])*")'
+
+    tokens = {
+        'root': [
+            (r'msc\b', Keyword.Type),
+            # Options
+            (r'(hscale|HSCALE|width|WIDTH|wordwraparcs|WORDWRAPARCS'
+             r'|arcgradient|ARCGRADIENT)\b', Name.Property),
+            # Operators
+            (r'(abox|ABOX|rbox|RBOX|box|BOX|note|NOTE)\b', Operator.Word),
+            (r'(\.|-|\|){3}', Keyword),
+            (r'(?:-|=|\.|:){2}'
+             r'|<<=>>|<->|<=>|<<>>|<:>'
+             r'|->|=>>|>>|=>|:>|-x|-X'
+             r'|<-|<<=|<<|<=|<:|x-|X-|=', Operator),
+            # Names
+            (r'\*', Name.Builtin),
+            (_var, Name.Variable),
+            # Other
+            (r'\[', Punctuation, 'attrs'),
+            (r'\{|\}|,|;', Punctuation),
+            include('comments')
+        ],
+        'attrs': [
+            (r'\]', Punctuation, '#pop'),
+            (_var + r'(\s*)(=)(\s*)' + _var,
+             bygroups(Name.Attribute, Whitespace, Operator, Whitespace,
+                      String)),
+            (r',', Punctuation),
+            include('comments')
+        ],
+        'comments': [
+            (r'(?://|#).*?\n', Comment.Single),
+            (r'/\*(?:.|\n)*?\*/', Comment.Multiline),
+            (r'[ \t\r\n]+', Whitespace)
+        ]
+    }
+
+
+class VGLLexer(RegexLexer):
+    """
+    For SampleManager VGL source code.
+    """
+    name = 'VGL'
+    url = 'http://www.thermoscientific.com/samplemanager'
+    aliases = ['vgl']
+    filenames = ['*.rpf']
+    version_added = '1.6'
+
+    flags = re.MULTILINE | re.DOTALL | re.IGNORECASE
+
+    tokens = {
+        'root': [
+            (r'\{[^}]*\}', Comment.Multiline),
+            (r'declare', Keyword.Constant),
+            (r'(if|then|else|endif|while|do|endwhile|and|or|prompt|object'
+             r'|create|on|line|with|global|routine|value|endroutine|constant'
+             r'|global|set|join|library|compile_option|file|exists|create|copy'
+             r'|delete|enable|windows|name|notprotected)(?! *[=<>.,()])',
+             Keyword),
+            (r'(true|false|null|empty|error|locked)', Keyword.Constant),
+            (r'[~^*#!%&\[\]()<>|+=:;,./?-]', Operator),
+            (r'"[^"]*"', String),
+            (r'(\.)([a-z_$][\w$]*)', bygroups(Operator, Name.Attribute)),
+            (r'[0-9][0-9]*(\.[0-9]+(e[+\-]?[0-9]+)?)?', Number),
+            (r'[a-z_$][\w$]*', Name),
+            (r'[\r\n]+', Whitespace),
+            (r'\s+', Whitespace)
+        ]
+    }
+
+
+class AlloyLexer(RegexLexer):
+    """
+    For Alloy source code.
+    """
+
+    name = 'Alloy'
+    url = 'http://alloy.mit.edu'
+    aliases = ['alloy']
+    filenames = ['*.als']
+    mimetypes = ['text/x-alloy']
+    version_added = '2.0'
+
+    flags = re.MULTILINE | re.DOTALL
+
+    iden_rex = r'[a-zA-Z_][\w]*"*'
+    string_rex = r'"\b(\\\\|\\[^\\]|[^"\\])*"'
+    text_tuple = (r'[^\S\n]+', Whitespace)
+
+    tokens = {
+        'sig': [
+            (r'(extends)\b', Keyword, '#pop'),
+            (iden_rex, Name),
+            text_tuple,
+            (r',', Punctuation),
+            (r'\{', Operator, '#pop'),
+        ],
+        'module': [
+            text_tuple,
+            (iden_rex, Name, '#pop'),
+        ],
+        'fun': [
+            text_tuple,
+            (r'\{', Operator, '#pop'),
+            (iden_rex, Name, '#pop'),
+        ],
+        'fact': [
+            include('fun'),
+            (string_rex, String, '#pop'),
+        ],
+        'root': [
+            (r'--.*?$', Comment.Single),
+            (r'//.*?$', Comment.Single),
+            (r'/\*.*?\*/', Comment.Multiline),
+            text_tuple,
+            (r'(module|open)(\s+)', bygroups(Keyword.Namespace, Whitespace),
+                'module'),
+            (r'(sig|enum)(\s+)', bygroups(Keyword.Declaration, Whitespace), 'sig'),
+            (r'(iden|univ|none)\b', Keyword.Constant),
+            (r'(int|Int)\b', Keyword.Type),
+            (r'(var|this|abstract|extends|set|seq|one|lone|let)\b', Keyword),
+            (r'(all|some|no|sum|disj|when|else)\b', Keyword),
+            (r'(run|check|for|but|exactly|expect|as|steps)\b', Keyword),
+            (r'(always|after|eventually|until|release)\b', Keyword), # future time operators
+            (r'(historically|before|once|since|triggered)\b', Keyword), # past time operators
+            (r'(and|or|implies|iff|in)\b', Operator.Word),
+            (r'(fun|pred|assert)(\s+)', bygroups(Keyword, Whitespace), 'fun'),
+            (r'(fact)(\s+)', bygroups(Keyword, Whitespace), 'fact'),
+            (r'!|#|&&|\+\+|<<|>>|>=|<=>|<=|\.\.|\.|->', Operator),
+            (r'[-+/*%=<>&!^|~{}\[\]().\';]', Operator),
+            (iden_rex, Name),
+            (r'[:,]', Punctuation),
+            (r'[0-9]+', Number.Integer),
+            (string_rex, String),
+            (r'\n', Whitespace),
+        ]
+    }
+
+
+class PanLexer(RegexLexer):
+    """
+    Lexer for pan source files.
+
+    Based on tcsh lexer.
+    """
+
+    name = 'Pan'
+    url = 'https://github.com/quattor/pan/'
+    aliases = ['pan']
+    filenames = ['*.pan']
+    version_added = '2.0'
+
+    tokens = {
+        'root': [
+            include('basic'),
+            (r'\(', Keyword, 'paren'),
+            (r'\{', Keyword, 'curly'),
+            include('data'),
+        ],
+        'basic': [
+            (words((
+                'if', 'for', 'with', 'else', 'type', 'bind', 'while', 'valid', 'final',
+                'prefix', 'unique', 'object', 'foreach', 'include', 'template',
+                'function', 'variable', 'structure', 'extensible', 'declaration'),
+                prefix=r'\b', suffix=r'\b'),
+             Keyword),
+            (words((
+                'file_contents', 'format', 'index', 'length', 'match', 'matches',
+                'replace', 'splice', 'split', 'substr', 'to_lowercase', 'to_uppercase',
+                'debug', 'error', 'traceback', 'deprecated', 'base64_decode',
+                'base64_encode', 'digest', 'escape', 'unescape', 'append', 'create',
+                'first', 'nlist', 'key', 'list', 'merge', 'next', 'prepend', 'is_boolean',
+                'is_defined', 'is_double', 'is_list', 'is_long', 'is_nlist', 'is_null',
+                'is_number', 'is_property', 'is_resource', 'is_string', 'to_boolean',
+                'to_double', 'to_long', 'to_string', 'clone', 'delete', 'exists',
+                'path_exists', 'if_exists', 'return', 'value'),
+                prefix=r'\b', suffix=r'\b'),
+             Name.Builtin),
+            (r'#.*', Comment),
+            (r'\\[\w\W]', String.Escape),
+            (r'(\b\w+)(\s*)(=)', bygroups(Name.Variable, Whitespace, Operator)),
+            (r'[\[\]{}()=]+', Operator),
+            (r'<<\s*(\'?)\\?(\w+)[\w\W]+?\2', String),
+            (r';', Punctuation),
+        ],
+        'data': [
+            (r'(?s)"(\\\\|\\[0-7]+|\\.|[^"\\])*"', String.Double),
+            (r"(?s)'(\\\\|\\[0-7]+|\\.|[^'\\])*'", String.Single),
+            (r'\s+', Whitespace),
+            (r'[^=\s\[\]{}()$"\'`\\;#]+', Text),
+            (r'\d+(?= |\Z)', Number),
+        ],
+        'curly': [
+            (r'\}', Keyword, '#pop'),
+            (r':-', Keyword),
+            (r'\w+', Name.Variable),
+            (r'[^}:"\'`$]+', Punctuation),
+            (r':', Punctuation),
+            include('root'),
+        ],
+        'paren': [
+            (r'\)', Keyword, '#pop'),
+            include('root'),
+        ],
+    }
+
+
+class CrmshLexer(RegexLexer):
+    """
+    Lexer for crmsh configuration files for Pacemaker clusters.
+    """
+    name = 'Crmsh'
+    url = 'http://crmsh.github.io/'
+    aliases = ['crmsh', 'pcmk']
+    filenames = ['*.crmsh', '*.pcmk']
+    mimetypes = []
+    version_added = '2.1'
+
+    elem = words((
+        'node', 'primitive', 'group', 'clone', 'ms', 'location',
+        'colocation', 'order', 'fencing_topology', 'rsc_ticket',
+        'rsc_template', 'property', 'rsc_defaults',
+        'op_defaults', 'acl_target', 'acl_group', 'user', 'role',
+        'tag'), suffix=r'(?![\w#$-])')
+    sub = words((
+        'params', 'meta', 'operations', 'op', 'rule',
+        'attributes', 'utilization'), suffix=r'(?![\w#$-])')
+    acl = words(('read', 'write', 'deny'), suffix=r'(?![\w#$-])')
+    bin_rel = words(('and', 'or'), suffix=r'(?![\w#$-])')
+    un_ops = words(('defined', 'not_defined'), suffix=r'(?![\w#$-])')
+    date_exp = words(('in_range', 'date', 'spec', 'in'), suffix=r'(?![\w#$-])')
+    acl_mod = (r'(?:tag|ref|reference|attribute|type|xpath)')
+    bin_ops = (r'(?:lt|gt|lte|gte|eq|ne)')
+    val_qual = (r'(?:string|version|number)')
+    rsc_role_action = (r'(?:Master|Started|Slave|Stopped|'
+                       r'start|promote|demote|stop)')
+
+    tokens = {
+        'root': [
+            (r'^(#.*)(\n)?', bygroups(Comment, Whitespace)),
+            # attr=value (nvpair)
+            (r'([\w#$-]+)(=)("(?:""|[^"])*"|\S+)',
+                bygroups(Name.Attribute, Punctuation, String)),
+            # need this construct, otherwise numeric node ids
+            # are matched as scores
+            # elem id:
+            (r'(node)(\s+)([\w#$-]+)(:)',
+                bygroups(Keyword, Whitespace, Name, Punctuation)),
+            # scores
+            (r'([+-]?([0-9]+|inf)):', Number),
+            # keywords (elements and other)
+            (elem, Keyword),
+            (sub, Keyword),
+            (acl, Keyword),
+            # binary operators
+            (rf'(?:{val_qual}:)?({bin_ops})(?![\w#$-])', Operator.Word),
+            # other operators
+            (bin_rel, Operator.Word),
+            (un_ops, Operator.Word),
+            (date_exp, Operator.Word),
+            # builtin attributes (e.g. #uname)
+            (r'#[a-z]+(?![\w#$-])', Name.Builtin),
+            # acl_mod:blah
+            (rf'({acl_mod})(:)("(?:""|[^"])*"|\S+)',
+             bygroups(Keyword, Punctuation, Name)),
+            # rsc_id[:(role|action)]
+            # NB: this matches all other identifiers
+            (rf'([\w#$-]+)(?:(:)({rsc_role_action}))?(?![\w#$-])',
+             bygroups(Name, Punctuation, Operator.Word)),
+            # punctuation
+            (r'(\\(?=\n)|[\[\](){}/:@])', Punctuation),
+            (r'\s+|\n', Whitespace),
+        ],
+    }
+
+
+class FlatlineLexer(RegexLexer):
+    """
+    Lexer for Flatline expressions.
+    """
+    name = 'Flatline'
+    url = 'https://github.com/bigmlcom/flatline'
+    aliases = ['flatline']
+    filenames = []
+    mimetypes = ['text/x-flatline']
+    version_added = '2.2'
+
+    special_forms = ('let',)
+
+    builtins = (
+        "!=", "*", "+", "-", "<", "<=", "=", ">", ">=", "abs", "acos", "all",
+        "all-but", "all-with-defaults", "all-with-numeric-default", "and",
+        "asin", "atan", "avg", "avg-window", "bin-center", "bin-count", "call",
+        "category-count", "ceil", "cond", "cond-window", "cons", "cos", "cosh",
+        "count", "diff-window", "div", "ensure-value", "ensure-weighted-value",
+        "epoch", "epoch-day", "epoch-fields", "epoch-hour", "epoch-millisecond",
+        "epoch-minute", "epoch-month", "epoch-second", "epoch-weekday",
+        "epoch-year", "exp", "f", "field", "field-prop", "fields", "filter",
+        "first", "floor", "head", "if", "in", "integer", "language", "length",
+        "levenshtein", "linear-regression", "list", "ln", "log", "log10", "map",
+        "matches", "matches?", "max", "maximum", "md5", "mean", "median", "min",
+        "minimum", "missing", "missing-count", "missing?", "missing_count",
+        "mod", "mode", "normalize", "not", "nth", "occurrences", "or",
+        "percentile", "percentile-label", "population", "population-fraction",
+        "pow", "preferred", "preferred?", "quantile-label", "rand", "rand-int",
+        "random-value", "re-quote", "real", "replace", "replace-first", "rest",
+        "round", "row-number", "segment-label", "sha1", "sha256", "sin", "sinh",
+        "sqrt", "square", "standard-deviation", "standard_deviation", "str",
+        "subs", "sum", "sum-squares", "sum-window", "sum_squares", "summary",
+        "summary-no", "summary-str", "tail", "tan", "tanh", "to-degrees",
+        "to-radians", "variance", "vectorize", "weighted-random-value", "window",
+        "winnow", "within-percentiles?", "z-score",
+    )
+
+    valid_name = r'(?!#)[\w!$%*+<=>?/.#-]+'
+
+    tokens = {
+        'root': [
+            # whitespaces - usually not relevant
+            (r'[,]+', Text),
+            (r'\s+', Whitespace),
+
+            # numbers
+            (r'-?\d+\.\d+', Number.Float),
+            (r'-?\d+', Number.Integer),
+            (r'0x-?[a-f\d]+', Number.Hex),
+
+            # strings, symbols and characters
+            (r'"(\\\\|\\[^\\]|[^"\\])*"', String),
+            (r"\\(.|[a-z]+)", String.Char),
+
+            # expression template placeholder
+            (r'_', String.Symbol),
+
+            # highlight the special forms
+            (words(special_forms, suffix=' '), Keyword),
+
+            # highlight the builtins
+            (words(builtins, suffix=' '), Name.Builtin),
+
+            # the remaining functions
+            (r'(?<=\()' + valid_name, Name.Function),
+
+            # find the remaining variables
+            (valid_name, Name.Variable),
+
+            # parentheses
+            (r'(\(|\))', Punctuation),
+        ],
+    }
+
+
+class SnowballLexer(ExtendedRegexLexer):
+    """
+    Lexer for Snowball source code.
+    """
+
+    name = 'Snowball'
+    url = 'https://snowballstem.org/'
+    aliases = ['snowball']
+    filenames = ['*.sbl']
+    version_added = '2.2'
+
+    _ws = r'\n\r\t '
+
+    def __init__(self, **options):
+        self._reset_stringescapes()
+        ExtendedRegexLexer.__init__(self, **options)
+
+    def _reset_stringescapes(self):
+        self._start = "'"
+        self._end = "'"
+
+    def _string(do_string_first):
+        def callback(lexer, match, ctx):
+            s = match.start()
+            text = match.group()
+            string = re.compile(rf'([^{re.escape(lexer._start)}]*)(.)').match
+            escape = re.compile(rf'([^{re.escape(lexer._end)}]*)(.)').match
+            pos = 0
+            do_string = do_string_first
+            while pos < len(text):
+                if do_string:
+                    match = string(text, pos)
+                    yield s + match.start(1), String.Single, match.group(1)
+                    if match.group(2) == "'":
+                        yield s + match.start(2), String.Single, match.group(2)
+                        ctx.stack.pop()
+                        break
+                    yield s + match.start(2), String.Escape, match.group(2)
+                    pos = match.end()
+                match = escape(text, pos)
+                yield s + match.start(), String.Escape, match.group()
+                if match.group(2) != lexer._end:
+                    ctx.stack[-1] = 'escape'
+                    break
+                pos = match.end()
+                do_string = True
+            ctx.pos = s + match.end()
+        return callback
+
+    def _stringescapes(lexer, match, ctx):
+        lexer._start = match.group(3)
+        lexer._end = match.group(5)
+        return bygroups(Keyword.Reserved, Whitespace, String.Escape, Whitespace,
+                        String.Escape)(lexer, match, ctx)
+
+    tokens = {
+        'root': [
+            (r'len\b', Name.Builtin),
+            (r'lenof\b', Operator.Word),
+            include('root1'),
+        ],
+        'root1': [
+            (rf'[{_ws}]+', Whitespace),
+            (r'\d+', Number.Integer),
+            (r"'", String.Single, 'string'),
+            (r'[()]', Punctuation),
+            (r'/\*[\w\W]*?\*/', Comment.Multiline),
+            (r'//.*', Comment.Single),
+            (r'[!*+\-/<=>]=|[-=]>|<[+-]|[$*+\-/<=>?\[\]]', Operator),
+            (words(('as', 'get', 'hex', 'among', 'define', 'decimal',
+                    'backwardmode'), suffix=r'\b'),
+             Keyword.Reserved),
+            (words(('strings', 'booleans', 'integers', 'routines', 'externals',
+                    'groupings'), suffix=r'\b'),
+             Keyword.Reserved, 'declaration'),
+            (words(('do', 'or', 'and', 'for', 'hop', 'non', 'not', 'set', 'try',
+                    'fail', 'goto', 'loop', 'next', 'test', 'true',
+                    'false', 'unset', 'atmark', 'attach', 'delete', 'gopast',
+                    'insert', 'repeat', 'sizeof', 'tomark', 'atleast',
+                    'atlimit', 'reverse', 'setmark', 'tolimit', 'setlimit',
+                    'backwards', 'substring'), suffix=r'\b'),
+             Operator.Word),
+            (words(('size', 'limit', 'cursor', 'maxint', 'minint'),
+                   suffix=r'\b'),
+             Name.Builtin),
+            (rf'(stringdef\b)([{_ws}]*)([^{_ws}]+)',
+             bygroups(Keyword.Reserved, Whitespace, String.Escape)),
+            (rf'(stringescapes\b)([{_ws}]*)(.)([{_ws}]*)(.)',
+             _stringescapes),
+            (r'[A-Za-z]\w*', Name),
+        ],
+        'declaration': [
+            (r'\)', Punctuation, '#pop'),
+            (words(('len', 'lenof'), suffix=r'\b'), Name,
+             ('root1', 'declaration')),
+            include('root1'),
+        ],
+        'string': [
+            (r"[^']*'", _string(True)),
+        ],
+        'escape': [
+            (r"[^']*'", _string(False)),
+        ],
+    }
+
+    def get_tokens_unprocessed(self, text=None, context=None):
+        self._reset_stringescapes()
+        return ExtendedRegexLexer.get_tokens_unprocessed(self, text, context)

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/esoteric.py

@@ -0,0 +1,300 @@
+"""
+    pygments.lexers.esoteric
+    ~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for esoteric languages.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, include, words, bygroups
+from pygments.token import Comment, Operator, Keyword, Name, String, Number, \
+    Punctuation, Error, Whitespace
+
+__all__ = ['BrainfuckLexer', 'BefungeLexer', 'RedcodeLexer', 'CAmkESLexer',
+           'CapDLLexer', 'AheuiLexer']
+
+
+class BrainfuckLexer(RegexLexer):
+    """
+    Lexer for the esoteric BrainFuck language.
+    """
+
+    name = 'Brainfuck'
+    url = 'http://www.muppetlabs.com/~breadbox/bf/'
+    aliases = ['brainfuck', 'bf']
+    filenames = ['*.bf', '*.b']
+    mimetypes = ['application/x-brainfuck']
+    version_added = ''
+
+    tokens = {
+        'common': [
+            # use different colors for different instruction types
+            (r'[.,]+', Name.Tag),
+            (r'[+-]+', Name.Builtin),
+            (r'[<>]+', Name.Variable),
+            (r'[^.,+\-<>\[\]]+', Comment),
+        ],
+        'root': [
+            (r'\[', Keyword, 'loop'),
+            (r'\]', Error),
+            include('common'),
+        ],
+        'loop': [
+            (r'\[', Keyword, '#push'),
+            (r'\]', Keyword, '#pop'),
+            include('common'),
+        ]
+    }
+
+    def analyse_text(text):
+        """It's safe to assume that a program which mostly consists of + -
+        and < > is brainfuck."""
+        plus_minus_count = 0
+        greater_less_count = 0
+
+        range_to_check = max(256, len(text))
+
+        for c in text[:range_to_check]:
+            if c == '+' or c == '-':
+                plus_minus_count += 1
+            if c == '<' or c == '>':
+                greater_less_count += 1
+
+        if plus_minus_count > (0.25 * range_to_check):
+            return 1.0
+        if greater_less_count > (0.25 * range_to_check):
+            return 1.0
+
+        result = 0
+        if '[-]' in text:
+            result += 0.5
+
+        return result
+
+
+class BefungeLexer(RegexLexer):
+    """
+    Lexer for the esoteric Befunge language.
+    """
+    name = 'Befunge'
+    url = 'http://en.wikipedia.org/wiki/Befunge'
+    aliases = ['befunge']
+    filenames = ['*.befunge']
+    mimetypes = ['application/x-befunge']
+    version_added = '0.7'
+
+    tokens = {
+        'root': [
+            (r'[0-9a-f]', Number),
+            (r'[+*/%!`-]', Operator),             # Traditional math
+            (r'[<>^v?\[\]rxjk]', Name.Variable),  # Move, imperatives
+            (r'[:\\$.,n]', Name.Builtin),         # Stack ops, imperatives
+            (r'[|_mw]', Keyword),
+            (r'[{}]', Name.Tag),                  # Befunge-98 stack ops
+            (r'".*?"', String.Double),            # Strings don't appear to allow escapes
+            (r'\'.', String.Single),              # Single character
+            (r'[#;]', Comment),                   # Trampoline... depends on direction hit
+            (r'[pg&~=@iotsy]', Keyword),          # Misc
+            (r'[()A-Z]', Comment),                # Fingerprints
+            (r'\s+', Whitespace),                 # Whitespace doesn't matter
+        ],
+    }
+
+
+class CAmkESLexer(RegexLexer):
+    """
+    Basic lexer for the input language for the CAmkES component platform.
+    """
+    name = 'CAmkES'
+    url = 'https://sel4.systems/CAmkES/'
+    aliases = ['camkes', 'idl4']
+    filenames = ['*.camkes', '*.idl4']
+    version_added = '2.1'
+
+    tokens = {
+        'root': [
+            # C pre-processor directive
+            (r'^(\s*)(#.*)(\n)', bygroups(Whitespace, Comment.Preproc,
+                Whitespace)),
+
+            # Whitespace, comments
+            (r'\s+', Whitespace),
+            (r'/\*(.|\n)*?\*/', Comment),
+            (r'//.*$', Comment),
+
+            (r'[\[(){},.;\]]', Punctuation),
+            (r'[~!%^&*+=|?:<>/-]', Operator),
+
+            (words(('assembly', 'attribute', 'component', 'composition',
+                    'configuration', 'connection', 'connector', 'consumes',
+                    'control', 'dataport', 'Dataport', 'Dataports', 'emits',
+                    'event', 'Event', 'Events', 'export', 'from', 'group',
+                    'hardware', 'has', 'interface', 'Interface', 'maybe',
+                    'procedure', 'Procedure', 'Procedures', 'provides',
+                    'template', 'thread', 'threads', 'to', 'uses', 'with'),
+                   suffix=r'\b'), Keyword),
+
+            (words(('bool', 'boolean', 'Buf', 'char', 'character', 'double',
+                    'float', 'in', 'inout', 'int', 'int16_6', 'int32_t',
+                    'int64_t', 'int8_t', 'integer', 'mutex', 'out', 'real',
+                    'refin', 'semaphore', 'signed', 'string', 'struct',
+                    'uint16_t', 'uint32_t', 'uint64_t', 'uint8_t', 'uintptr_t',
+                    'unsigned', 'void'),
+                   suffix=r'\b'), Keyword.Type),
+
+            # Recognised attributes
+            (r'[a-zA-Z_]\w*_(priority|domain|buffer)', Keyword.Reserved),
+            (words(('dma_pool', 'from_access', 'to_access'), suffix=r'\b'),
+                Keyword.Reserved),
+
+            # CAmkES-level include
+            (r'(import)(\s+)((?:<[^>]*>|"[^"]*");)',
+                bygroups(Comment.Preproc, Whitespace, Comment.Preproc)),
+
+            # C-level include
+            (r'(include)(\s+)((?:<[^>]*>|"[^"]*");)',
+                bygroups(Comment.Preproc, Whitespace, Comment.Preproc)),
+
+            # Literals
+            (r'0[xX][\da-fA-F]+', Number.Hex),
+            (r'-?[\d]+', Number),
+            (r'-?[\d]+\.[\d]+', Number.Float),
+            (r'"[^"]*"', String),
+            (r'[Tt]rue|[Ff]alse', Name.Builtin),
+
+            # Identifiers
+            (r'[a-zA-Z_]\w*', Name),
+        ],
+    }
+
+
+class CapDLLexer(RegexLexer):
+    """
+    Basic lexer for CapDL.
+
+    The source of the primary tool that reads such specifications is available
+    at https://github.com/seL4/capdl/tree/master/capDL-tool. Note that this
+    lexer only supports a subset of the grammar. For example, identifiers can
+    shadow type names, but these instances are currently incorrectly
+    highlighted as types. Supporting this would need a stateful lexer that is
+    considered unnecessarily complex for now.
+    """
+    name = 'CapDL'
+    url = 'https://ssrg.nicta.com.au/publications/nictaabstracts/Kuz_KLW_10.abstract.pml'
+    aliases = ['capdl']
+    filenames = ['*.cdl']
+    version_added = '2.2'
+
+    tokens = {
+        'root': [
+            # C pre-processor directive
+            (r'^(\s*)(#.*)(\n)',
+                bygroups(Whitespace, Comment.Preproc, Whitespace)),
+
+            # Whitespace, comments
+            (r'\s+', Whitespace),
+            (r'/\*(.|\n)*?\*/', Comment),
+            (r'(//|--).*$', Comment),
+
+            (r'[<>\[(){},:;=\]]', Punctuation),
+            (r'\.\.', Punctuation),
+
+            (words(('arch', 'arm11', 'caps', 'child_of', 'ia32', 'irq', 'maps',
+                    'objects'), suffix=r'\b'), Keyword),
+
+            (words(('aep', 'asid_pool', 'cnode', 'ep', 'frame', 'io_device',
+                    'io_ports', 'io_pt', 'notification', 'pd', 'pt', 'tcb',
+                    'ut', 'vcpu'), suffix=r'\b'), Keyword.Type),
+
+            # Properties
+            (words(('asid', 'addr', 'badge', 'cached', 'dom', 'domainID', 'elf',
+                    'fault_ep', 'G', 'guard', 'guard_size', 'init', 'ip',
+                    'prio', 'sp', 'R', 'RG', 'RX', 'RW', 'RWG', 'RWX', 'W',
+                    'WG', 'WX', 'level', 'masked', 'master_reply', 'paddr',
+                    'ports', 'reply', 'uncached'), suffix=r'\b'),
+             Keyword.Reserved),
+
+            # Literals
+            (r'0[xX][\da-fA-F]+', Number.Hex),
+            (r'\d+(\.\d+)?(k|M)?', Number),
+            (words(('bits',), suffix=r'\b'), Number),
+            (words(('cspace', 'vspace', 'reply_slot', 'caller_slot',
+                    'ipc_buffer_slot'), suffix=r'\b'), Number),
+
+            # Identifiers
+            (r'[a-zA-Z_][-@\.\w]*', Name),
+        ],
+    }
+
+
+class RedcodeLexer(RegexLexer):
+    """
+    A simple Redcode lexer based on ICWS'94.
+    Contributed by Adam Blinkinsop <blinks@acm.org>.
+    """
+    name = 'Redcode'
+    aliases = ['redcode']
+    filenames = ['*.cw']
+    url = 'https://en.wikipedia.org/wiki/Core_War'
+    version_added = '0.8'
+
+    opcodes = ('DAT', 'MOV', 'ADD', 'SUB', 'MUL', 'DIV', 'MOD',
+               'JMP', 'JMZ', 'JMN', 'DJN', 'CMP', 'SLT', 'SPL',
+               'ORG', 'EQU', 'END')
+    modifiers = ('A', 'B', 'AB', 'BA', 'F', 'X', 'I')
+
+    tokens = {
+        'root': [
+            # Whitespace:
+            (r'\s+', Whitespace),
+            (r';.*$', Comment.Single),
+            # Lexemes:
+            #  Identifiers
+            (r'\b({})\b'.format('|'.join(opcodes)), Name.Function),
+            (r'\b({})\b'.format('|'.join(modifiers)), Name.Decorator),
+            (r'[A-Za-z_]\w+', Name),
+            #  Operators
+            (r'[-+*/%]', Operator),
+            (r'[#$@<>]', Operator),  # mode
+            (r'[.,]', Punctuation),  # mode
+            #  Numbers
+            (r'[-+]?\d+', Number.Integer),
+        ],
+    }
+
+
+class AheuiLexer(RegexLexer):
+    """
+    Aheui is esoteric language based on Korean alphabets.
+    """
+
+    name = 'Aheui'
+    url = 'http://aheui.github.io/'
+    aliases = ['aheui']
+    filenames = ['*.aheui']
+    version_added = ''
+
+    tokens = {
+        'root': [
+            ('['
+             '나-낳냐-냫너-넣녀-녛노-놓뇨-눟뉴-닇'
+             '다-닿댜-댷더-덯뎌-뎧도-돟됴-둫듀-딓'
+             '따-땋땨-떃떠-떻뗘-뗳또-똫뚀-뚷뜌-띟'
+             '라-랗랴-럏러-렇려-렿로-롷료-뤃류-릫'
+             '마-맣먀-먛머-멓며-몋모-뫃묘-뭏뮤-믷'
+             '바-밯뱌-뱧버-벟벼-볗보-봏뵤-붛뷰-빃'
+             '빠-빻뺘-뺳뻐-뻫뼈-뼣뽀-뽛뾰-뿧쀼-삏'
+             '사-샇샤-샿서-섷셔-셯소-솧쇼-숳슈-싛'
+             '싸-쌓쌰-썋써-쎃쎠-쎻쏘-쏳쑈-쑿쓔-씧'
+             '자-잫쟈-쟣저-젛져-졓조-좋죠-줗쥬-즿'
+             '차-챃챠-챻처-첳쳐-쳫초-촣쵸-춯츄-칗'
+             '카-캏캬-컇커-컿켜-켷코-콯쿄-쿻큐-킣'
+             '타-탛탸-턓터-텋텨-톃토-톻툐-퉇튜-틯'
+             '파-팧퍄-퍟퍼-펗펴-폏포-퐇표-풓퓨-픻'
+             '하-핳햐-햫허-헣혀-혛호-홓효-훟휴-힇'
+             ']', Operator),
+            ('.', Comment),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/fortran.py

@@ -0,0 +1,212 @@
+"""
+    pygments.lexers.fortran
+    ~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for Fortran languages.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, bygroups, include, words, using, default
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Generic
+
+__all__ = ['FortranLexer', 'FortranFixedLexer']
+
+
+class FortranLexer(RegexLexer):
+    """
+    Lexer for FORTRAN 90 code.
+    """
+    name = 'Fortran'
+    url = 'https://fortran-lang.org/'
+    aliases = ['fortran', 'f90']
+    filenames = ['*.f03', '*.f90', '*.F03', '*.F90']
+    mimetypes = ['text/x-fortran']
+    version_added = '0.10'
+    flags = re.IGNORECASE | re.MULTILINE
+
+    # Data Types: INTEGER, REAL, COMPLEX, LOGICAL, CHARACTER and DOUBLE PRECISION
+    # Operators: **, *, +, -, /, <, >, <=, >=, ==, /=
+    # Logical (?): NOT, AND, OR, EQV, NEQV
+
+    # Builtins:
+    # http://gcc.gnu.org/onlinedocs/gcc-3.4.6/g77/Table-of-Intrinsic-Functions.html
+
+    tokens = {
+        'root': [
+            (r'^#.*\n', Comment.Preproc),
+            (r'!.*\n', Comment),
+            include('strings'),
+            include('core'),
+            (r'[a-z][\w$]*', Name),
+            include('nums'),
+            (r'[\s]+', Text.Whitespace),
+        ],
+        'core': [
+            # Statements
+
+            (r'\b(DO)(\s+)(CONCURRENT)\b', bygroups(Keyword, Text.Whitespace, Keyword)),
+            (r'\b(GO)(\s*)(TO)\b', bygroups(Keyword, Text.Whitespace, Keyword)),
+
+            (words((
+                'ABSTRACT', 'ACCEPT', 'ALL', 'ALLSTOP', 'ALLOCATABLE', 'ALLOCATE',
+                'ARRAY', 'ASSIGN', 'ASSOCIATE', 'ASYNCHRONOUS', 'BACKSPACE', 'BIND',
+                'BLOCK', 'BLOCKDATA', 'BYTE', 'CALL', 'CASE', 'CLASS', 'CLOSE',
+                'CODIMENSION', 'COMMON', 'CONTIGUOUS', 'CONTAINS',
+                'CONTINUE', 'CRITICAL', 'CYCLE', 'DATA', 'DEALLOCATE', 'DECODE',
+                'DEFERRED', 'DIMENSION', 'DO', 'ELEMENTAL', 'ELSE', 'ELSEIF', 'ENCODE',
+                'END', 'ENDASSOCIATE', 'ENDBLOCK', 'ENDDO', 'ENDENUM', 'ENDFORALL',
+                'ENDFUNCTION',  'ENDIF', 'ENDINTERFACE', 'ENDMODULE', 'ENDPROGRAM',
+                'ENDSELECT', 'ENDSUBMODULE', 'ENDSUBROUTINE', 'ENDTYPE', 'ENDWHERE',
+                'ENTRY', 'ENUM', 'ENUMERATOR', 'EQUIVALENCE', 'ERROR STOP', 'EXIT',
+                'EXTENDS', 'EXTERNAL', 'EXTRINSIC', 'FILE', 'FINAL', 'FORALL', 'FORMAT',
+                'FUNCTION', 'GENERIC', 'IF', 'IMAGES', 'IMPLICIT',
+                'IMPORT', 'IMPURE', 'INCLUDE', 'INQUIRE', 'INTENT', 'INTERFACE',
+                'INTRINSIC', 'IS', 'LOCK', 'MEMORY', 'MODULE', 'NAMELIST', 'NULLIFY',
+                'NONE', 'NON_INTRINSIC', 'NON_OVERRIDABLE', 'NOPASS', 'ONLY', 'OPEN',
+                'OPTIONAL', 'OPTIONS', 'PARAMETER', 'PASS', 'PAUSE', 'POINTER', 'PRINT',
+                'PRIVATE', 'PROGRAM', 'PROCEDURE', 'PROTECTED', 'PUBLIC', 'PURE', 'READ',
+                'RECURSIVE', 'RESULT', 'RETURN', 'REWIND', 'SAVE', 'SELECT', 'SEQUENCE',
+                'STOP', 'SUBMODULE', 'SUBROUTINE', 'SYNC', 'SYNCALL', 'SYNCIMAGES',
+                'SYNCMEMORY', 'TARGET', 'THEN', 'TYPE', 'UNLOCK', 'USE', 'VALUE',
+                'VOLATILE', 'WHERE', 'WRITE', 'WHILE'), prefix=r'\b', suffix=r'\s*\b'),
+             Keyword),
+
+            # Data Types
+            (words((
+                'CHARACTER', 'COMPLEX', 'DOUBLE PRECISION', 'DOUBLE COMPLEX', 'INTEGER',
+                'LOGICAL', 'REAL', 'C_INT', 'C_SHORT', 'C_LONG', 'C_LONG_LONG',
+                'C_SIGNED_CHAR', 'C_SIZE_T', 'C_INT8_T', 'C_INT16_T', 'C_INT32_T',
+                'C_INT64_T', 'C_INT_LEAST8_T', 'C_INT_LEAST16_T', 'C_INT_LEAST32_T',
+                'C_INT_LEAST64_T', 'C_INT_FAST8_T', 'C_INT_FAST16_T', 'C_INT_FAST32_T',
+                'C_INT_FAST64_T', 'C_INTMAX_T', 'C_INTPTR_T', 'C_FLOAT', 'C_DOUBLE',
+                'C_LONG_DOUBLE', 'C_FLOAT_COMPLEX', 'C_DOUBLE_COMPLEX',
+                'C_LONG_DOUBLE_COMPLEX', 'C_BOOL', 'C_CHAR', 'C_PTR', 'C_FUNPTR'),
+                   prefix=r'\b', suffix=r'\s*\b'),
+             Keyword.Type),
+
+            # Operators
+            (r'(\*\*|\*|\+|-|\/|<|>|<=|>=|==|\/=|=)', Operator),
+
+            (r'(::)', Keyword.Declaration),
+
+            (r'[()\[\],:&%;.]', Punctuation),
+            # Intrinsics
+            (words((
+                'Abort', 'Abs', 'Access', 'AChar', 'ACos', 'ACosH', 'AdjustL',
+                'AdjustR', 'AImag', 'AInt', 'Alarm', 'All', 'Allocated', 'ALog',
+                'AMax', 'AMin', 'AMod', 'And', 'ANInt', 'Any', 'ASin', 'ASinH',
+                'Associated', 'ATan', 'ATanH', 'Atomic_Define', 'Atomic_Ref',
+                'BesJ', 'BesJN', 'Bessel_J0', 'Bessel_J1', 'Bessel_JN', 'Bessel_Y0',
+                'Bessel_Y1', 'Bessel_YN', 'BesY', 'BesYN', 'BGE', 'BGT', 'BLE',
+                'BLT', 'Bit_Size', 'BTest', 'CAbs', 'CCos', 'Ceiling', 'CExp',
+                'Char', 'ChDir', 'ChMod', 'CLog', 'Cmplx', 'Command_Argument_Count',
+                'Complex', 'Conjg', 'Cos', 'CosH', 'Count', 'CPU_Time', 'CShift',
+                'CSin', 'CSqRt', 'CTime', 'C_Loc', 'C_Associated',
+                'C_Null_Ptr', 'C_Null_Funptr', 'C_F_Pointer', 'C_F_ProcPointer',
+                'C_Null_Char', 'C_Alert', 'C_Backspace', 'C_Form_Feed', 'C_FunLoc',
+                'C_Sizeof', 'C_New_Line', 'C_Carriage_Return',
+                'C_Horizontal_Tab', 'C_Vertical_Tab', 'DAbs', 'DACos', 'DASin',
+                'DATan', 'Date_and_Time', 'DbesJ', 'DbesJN', 'DbesY',
+                'DbesYN', 'Dble', 'DCos', 'DCosH', 'DDiM', 'DErF',
+                'DErFC', 'DExp', 'Digits', 'DiM', 'DInt', 'DLog', 'DMax',
+                'DMin', 'DMod', 'DNInt', 'Dot_Product', 'DProd', 'DSign', 'DSinH',
+                'DShiftL', 'DShiftR', 'DSin', 'DSqRt', 'DTanH', 'DTan', 'DTime',
+                'EOShift', 'Epsilon', 'ErF', 'ErFC', 'ErFC_Scaled', 'ETime',
+                'Execute_Command_Line', 'Exit', 'Exp', 'Exponent', 'Extends_Type_Of',
+                'FDate', 'FGet', 'FGetC', 'FindLoc', 'Float', 'Floor', 'Flush',
+                'FNum', 'FPutC', 'FPut', 'Fraction', 'FSeek', 'FStat', 'FTell',
+                'Gamma', 'GError', 'GetArg', 'Get_Command', 'Get_Command_Argument',
+                'Get_Environment_Variable', 'GetCWD', 'GetEnv', 'GetGId', 'GetLog',
+                'GetPId', 'GetUId', 'GMTime', 'HostNm', 'Huge', 'Hypot', 'IAbs',
+                'IAChar', 'IAll', 'IAnd', 'IAny', 'IArgC', 'IBClr', 'IBits',
+                'IBSet', 'IChar', 'IDate', 'IDiM', 'IDInt', 'IDNInt', 'IEOr',
+                'IErrNo', 'IFix', 'Imag', 'ImagPart', 'Image_Index', 'Index',
+                'Int', 'IOr', 'IParity', 'IRand', 'IsaTty', 'IShft', 'IShftC',
+                'ISign', 'Iso_C_Binding', 'Is_Contiguous', 'Is_Iostat_End',
+                'Is_Iostat_Eor', 'ITime', 'Kill', 'Kind', 'LBound', 'LCoBound',
+                'Len', 'Len_Trim', 'LGe', 'LGt', 'Link', 'LLe', 'LLt', 'LnBlnk',
+                'Loc', 'Log', 'Log_Gamma', 'Logical', 'Long', 'LShift', 'LStat',
+                'LTime', 'MaskL', 'MaskR', 'MatMul', 'Max', 'MaxExponent',
+                'MaxLoc', 'MaxVal', 'MClock', 'Merge', 'Merge_Bits', 'Move_Alloc',
+                'Min', 'MinExponent', 'MinLoc', 'MinVal', 'Mod', 'Modulo', 'MvBits',
+                'Nearest', 'New_Line', 'NInt', 'Norm2', 'Not', 'Null', 'Num_Images',
+                'Or', 'Pack', 'Parity', 'PError', 'Precision', 'Present', 'Product',
+                'Radix', 'Rand', 'Random_Number', 'Random_Seed', 'Range', 'Real',
+                'RealPart', 'Rename', 'Repeat', 'Reshape', 'RRSpacing', 'RShift',
+                'Same_Type_As', 'Scale', 'Scan', 'Second', 'Selected_Char_Kind',
+                'Selected_Int_Kind', 'Selected_Real_Kind', 'Set_Exponent', 'Shape',
+                'ShiftA', 'ShiftL', 'ShiftR', 'Short', 'Sign', 'Signal', 'SinH',
+                'Sin', 'Sleep', 'Sngl', 'Spacing', 'Spread', 'SqRt', 'SRand',
+                'Stat', 'Storage_Size', 'Sum', 'SymLnk', 'System', 'System_Clock',
+                'Tan', 'TanH', 'Time', 'This_Image', 'Tiny', 'TrailZ', 'Transfer',
+                'Transpose', 'Trim', 'TtyNam', 'UBound', 'UCoBound', 'UMask',
+                'Unlink', 'Unpack', 'Verify', 'XOr', 'ZAbs', 'ZCos', 'ZExp',
+                'ZLog', 'ZSin', 'ZSqRt'), prefix=r'\b', suffix=r'\s*\b'),
+             Name.Builtin),
+
+            # Booleans
+            (r'\.(true|false)\.', Name.Builtin),
+            # Comparing Operators
+            (r'\.(eq|ne|lt|le|gt|ge|not|and|or|eqv|neqv)\.', Operator.Word),
+        ],
+
+        'strings': [
+            (r'"(\\[0-7]+|\\[^0-7]|[^"\\])*"', String.Double),
+            (r"'(\\[0-7]+|\\[^0-7]|[^'\\])*'", String.Single),
+        ],
+
+        'nums': [
+            (r'\d+(?![.e])(_([1-9]|[a-z]\w*))?', Number.Integer),
+            (r'[+-]?\d*\.\d+([ed][-+]?\d+)?(_([1-9]|[a-z]\w*))?', Number.Float),
+            (r'[+-]?\d+\.\d*([ed][-+]?\d+)?(_([1-9]|[a-z]\w*))?', Number.Float),
+            (r'[+-]?\d+(\.\d*)?[ed][-+]?\d+(_([1-9]|[a-z]\w*))?', Number.Float),
+        ],
+    }
+
+
+class FortranFixedLexer(RegexLexer):
+    """
+    Lexer for fixed format Fortran.
+    """
+    name = 'FortranFixed'
+    aliases = ['fortranfixed']
+    filenames = ['*.f', '*.F']
+    url = 'https://fortran-lang.org/'
+    version_added = '2.1'
+
+    flags = re.IGNORECASE
+
+    def _lex_fortran(self, match, ctx=None):
+        """Lex a line just as free form fortran without line break."""
+        lexer = FortranLexer()
+        text = match.group(0) + "\n"
+        for index, token, value in lexer.get_tokens_unprocessed(text):
+            value = value.replace('\n', '')
+            if value != '':
+                yield index, token, value
+
+    tokens = {
+        'root': [
+            (r'[C*].*\n', Comment),
+            (r'#.*\n', Comment.Preproc),
+            (r' {0,4}!.*\n', Comment),
+            (r'(.{5})', Name.Label, 'cont-char'),
+            (r'.*\n', using(FortranLexer)),
+        ],
+        'cont-char': [
+            (' ', Text, 'code'),
+            ('0', Comment, 'code'),
+            ('.', Generic.Strong, 'code'),
+        ],
+        'code': [
+            (r'(.{66})(.*)(\n)',
+             bygroups(_lex_fortran, Comment, Text.Whitespace), 'root'),
+            (r'(.*)(\n)', bygroups(_lex_fortran, Text.Whitespace), 'root'),
+            default('root'),
+        ]
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/gleam.py

@@ -0,0 +1,74 @@
+"""
+    pygments.lexers.gleam
+    ~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for the Gleam programming language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, words, bygroups
+from pygments.token import Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Whitespace
+
+__all__ = ['GleamLexer']
+
+
+class GleamLexer(RegexLexer):
+    """
+    Lexer for the Gleam programming language (version 1.0.0).
+    """
+
+    name = 'Gleam'
+    url = 'https://gleam.run/'
+    filenames = ['*.gleam']
+    aliases = ['gleam']
+    mimetypes = ['text/x-gleam']
+    version_added = '2.19'
+
+    keywords = words((
+        'as', 'assert', 'auto', 'case', 'const', 'delegate', 'derive', 'echo',
+        'else', 'fn', 'if', 'implement', 'import', 'let', 'macro', 'opaque',
+        'panic', 'pub', 'test', 'todo', 'type', 'use',
+    ), suffix=r'\b')
+
+    tokens = {
+        'root': [
+            # Comments
+            (r'(///.*?)(\n)', bygroups(String.Doc, Whitespace)),
+            (r'(//.*?)(\n)', bygroups(Comment.Single, Whitespace)),
+
+            # Keywords
+            (keywords, Keyword),
+            (r'([a-zA-Z_]+)(\.)', bygroups(Keyword, Punctuation)),
+
+            # Punctuation
+            (r'[()\[\]{}:;,@]+', Punctuation),
+            (r'(#|!=|!|==|\|>|\|\||\||\->|<\-|&&|<<|>>|\.\.|\.|=)', Punctuation),
+
+            # Operators
+            (r'(<>|\+\.?|\-\.?|\*\.?|/\.?|%\.?|<=\.?|>=\.?|<\.?|>\.?|=)', Operator),
+
+            # Strings
+            (r'"(\\"|[^"])*"', String),
+
+            # Identifiers
+            (r'\b(let)(\s+)(\w+)', bygroups(Keyword, Whitespace, Name.Variable)),
+            (r'\b(fn)(\s+)(\w+)', bygroups(Keyword, Whitespace, Name.Function)),
+            (r'[a-zA-Z_/]\w*', Name),
+
+            # numbers
+            (r'(\d+(_\d+)*\.(?!\.)(\d+(_\d+)*)?|\.\d+(_\d+)*)([eEf][+-]?[0-9]+)?', Number.Float),
+            (r'\d+(_\d+)*[eEf][+-]?[0-9]+', Number.Float),
+            (r'0[xX][a-fA-F0-9]+(_[a-fA-F0-9]+)*(\.([a-fA-F0-9]+(_[a-fA-F0-9]+)*)?)?p[+-]?\d+', Number.Float),
+            (r'0[bB][01]+(_[01]+)*', Number.Bin),
+            (r'0[oO][0-7]+(_[0-7]+)*', Number.Oct),
+            (r'0[xX][a-fA-F0-9]+(_[a-fA-F0-9]+)*', Number.Hex),
+            (r'\d+(_\d+)*', Number.Integer),
+
+            # Whitespace
+            (r'\s+', Whitespace),
+
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/haxe.py

@@ -0,0 +1,941 @@
+"""
+    pygments.lexers.haxe
+    ~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for Haxe and related stuff.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import ExtendedRegexLexer, RegexLexer, include, bygroups, \
+    default
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Generic, Whitespace
+
+__all__ = ['HaxeLexer', 'HxmlLexer']
+
+
+class HaxeLexer(ExtendedRegexLexer):
+    """
+    For Haxe source code.
+    """
+
+    name = 'Haxe'
+    url = 'http://haxe.org/'
+    aliases = ['haxe', 'hxsl', 'hx']
+    filenames = ['*.hx', '*.hxsl']
+    mimetypes = ['text/haxe', 'text/x-haxe', 'text/x-hx']
+    version_added = '1.3'
+
+    # keywords extracted from lexer.mll in the haxe compiler source
+    keyword = (r'(?:function|class|static|var|if|else|while|do|for|'
+               r'break|return|continue|extends|implements|import|'
+               r'switch|case|default|public|private|try|untyped|'
+               r'catch|new|this|throw|extern|enum|in|interface|'
+               r'cast|override|dynamic|typedef|package|'
+               r'inline|using|null|true|false|abstract)\b')
+
+    # idtype in lexer.mll
+    typeid = r'_*[A-Z]\w*'
+
+    # combined ident and dollar and idtype
+    ident = r'(?:_*[a-z]\w*|_+[0-9]\w*|' + typeid + r'|_+|\$\w+)'
+
+    binop = (r'(?:%=|&=|\|=|\^=|\+=|\-=|\*=|/=|<<=|>\s*>\s*=|>\s*>\s*>\s*=|==|'
+             r'!=|<=|>\s*=|&&|\|\||<<|>>>|>\s*>|\.\.\.|<|>|%|&|\||\^|\+|\*|'
+             r'/|\-|=>|=)')
+
+    # ident except keywords
+    ident_no_keyword = r'(?!' + keyword + ')' + ident
+
+    flags = re.DOTALL | re.MULTILINE
+
+    preproc_stack = []
+
+    def preproc_callback(self, match, ctx):
+        proc = match.group(2)
+
+        if proc == 'if':
+            # store the current stack
+            self.preproc_stack.append(ctx.stack[:])
+        elif proc in ['else', 'elseif']:
+            # restore the stack back to right before #if
+            if self.preproc_stack:
+                ctx.stack = self.preproc_stack[-1][:]
+        elif proc == 'end':
+            # remove the saved stack of previous #if
+            if self.preproc_stack:
+                self.preproc_stack.pop()
+
+        # #if and #elseif should follow by an expr
+        if proc in ['if', 'elseif']:
+            ctx.stack.append('preproc-expr')
+
+        # #error can be optionally follow by the error msg
+        if proc in ['error']:
+            ctx.stack.append('preproc-error')
+
+        yield match.start(), Comment.Preproc, '#' + proc
+        ctx.pos = match.end()
+
+    tokens = {
+        'root': [
+            include('spaces'),
+            include('meta'),
+            (r'(?:package)\b', Keyword.Namespace, ('semicolon', 'package')),
+            (r'(?:import)\b', Keyword.Namespace, ('semicolon', 'import')),
+            (r'(?:using)\b', Keyword.Namespace, ('semicolon', 'using')),
+            (r'(?:extern|private)\b', Keyword.Declaration),
+            (r'(?:abstract)\b', Keyword.Declaration, 'abstract'),
+            (r'(?:class|interface)\b', Keyword.Declaration, 'class'),
+            (r'(?:enum)\b', Keyword.Declaration, 'enum'),
+            (r'(?:typedef)\b', Keyword.Declaration, 'typedef'),
+
+            # top-level expression
+            # although it is not supported in haxe, but it is common to write
+            # expression in web pages the positive lookahead here is to prevent
+            # an infinite loop at the EOF
+            (r'(?=.)', Text, 'expr-statement'),
+        ],
+
+        # space/tab/comment/preproc
+        'spaces': [
+            (r'\s+', Whitespace),
+            (r'//[^\n\r]*', Comment.Single),
+            (r'/\*.*?\*/', Comment.Multiline),
+            (r'(#)(if|elseif|else|end|error)\b', preproc_callback),
+        ],
+
+        'string-single-interpol': [
+            (r'\$\{', String.Interpol, ('string-interpol-close', 'expr')),
+            (r'\$\$', String.Escape),
+            (r'\$(?=' + ident + ')', String.Interpol, 'ident'),
+            include('string-single'),
+        ],
+
+        'string-single': [
+            (r"'", String.Single, '#pop'),
+            (r'\\.', String.Escape),
+            (r'.', String.Single),
+        ],
+
+        'string-double': [
+            (r'"', String.Double, '#pop'),
+            (r'\\.', String.Escape),
+            (r'.', String.Double),
+        ],
+
+        'string-interpol-close': [
+            (r'\$'+ident, String.Interpol),
+            (r'\}', String.Interpol, '#pop'),
+        ],
+
+        'package': [
+            include('spaces'),
+            (ident, Name.Namespace),
+            (r'\.', Punctuation, 'import-ident'),
+            default('#pop'),
+        ],
+
+        'import': [
+            include('spaces'),
+            (ident, Name.Namespace),
+            (r'\*', Keyword),  # wildcard import
+            (r'\.', Punctuation, 'import-ident'),
+            (r'in', Keyword.Namespace, 'ident'),
+            default('#pop'),
+        ],
+
+        'import-ident': [
+            include('spaces'),
+            (r'\*', Keyword, '#pop'),  # wildcard import
+            (ident, Name.Namespace, '#pop'),
+        ],
+
+        'using': [
+            include('spaces'),
+            (ident, Name.Namespace),
+            (r'\.', Punctuation, 'import-ident'),
+            default('#pop'),
+        ],
+
+        'preproc-error': [
+            (r'\s+', Whitespace),
+            (r"'", String.Single, ('#pop', 'string-single')),
+            (r'"', String.Double, ('#pop', 'string-double')),
+            default('#pop'),
+        ],
+
+        'preproc-expr': [
+            (r'\s+', Whitespace),
+            (r'\!', Comment.Preproc),
+            (r'\(', Comment.Preproc, ('#pop', 'preproc-parenthesis')),
+
+            (ident, Comment.Preproc, '#pop'),
+
+            # Float
+            (r'\.[0-9]+', Number.Float),
+            (r'[0-9]+[eE][+\-]?[0-9]+', Number.Float),
+            (r'[0-9]+\.[0-9]*[eE][+\-]?[0-9]+', Number.Float),
+            (r'[0-9]+\.[0-9]+', Number.Float),
+            (r'[0-9]+\.(?!' + ident + r'|\.\.)', Number.Float),
+
+            # Int
+            (r'0x[0-9a-fA-F]+', Number.Hex),
+            (r'[0-9]+', Number.Integer),
+
+            # String
+            (r"'", String.Single, ('#pop', 'string-single')),
+            (r'"', String.Double, ('#pop', 'string-double')),
+        ],
+
+        'preproc-parenthesis': [
+            (r'\s+', Whitespace),
+            (r'\)', Comment.Preproc, '#pop'),
+            default('preproc-expr-in-parenthesis'),
+        ],
+
+        'preproc-expr-chain': [
+            (r'\s+', Whitespace),
+            (binop, Comment.Preproc, ('#pop', 'preproc-expr-in-parenthesis')),
+            default('#pop'),
+        ],
+
+        # same as 'preproc-expr' but able to chain 'preproc-expr-chain'
+        'preproc-expr-in-parenthesis': [
+            (r'\s+', Whitespace),
+            (r'\!', Comment.Preproc),
+            (r'\(', Comment.Preproc,
+             ('#pop', 'preproc-expr-chain', 'preproc-parenthesis')),
+
+            (ident, Comment.Preproc, ('#pop', 'preproc-expr-chain')),
+
+            # Float
+            (r'\.[0-9]+', Number.Float, ('#pop', 'preproc-expr-chain')),
+            (r'[0-9]+[eE][+\-]?[0-9]+', Number.Float, ('#pop', 'preproc-expr-chain')),
+            (r'[0-9]+\.[0-9]*[eE][+\-]?[0-9]+', Number.Float, ('#pop', 'preproc-expr-chain')),
+            (r'[0-9]+\.[0-9]+', Number.Float, ('#pop', 'preproc-expr-chain')),
+            (r'[0-9]+\.(?!' + ident + r'|\.\.)', Number.Float, ('#pop', 'preproc-expr-chain')),
+
+            # Int
+            (r'0x[0-9a-fA-F]+', Number.Hex, ('#pop', 'preproc-expr-chain')),
+            (r'[0-9]+', Number.Integer, ('#pop', 'preproc-expr-chain')),
+
+            # String
+            (r"'", String.Single,
+             ('#pop', 'preproc-expr-chain', 'string-single')),
+            (r'"', String.Double,
+             ('#pop', 'preproc-expr-chain', 'string-double')),
+        ],
+
+        'abstract': [
+            include('spaces'),
+            default(('#pop', 'abstract-body', 'abstract-relation',
+                    'abstract-opaque', 'type-param-constraint', 'type-name')),
+        ],
+
+        'abstract-body': [
+            include('spaces'),
+            (r'\{', Punctuation, ('#pop', 'class-body')),
+        ],
+
+        'abstract-opaque': [
+            include('spaces'),
+            (r'\(', Punctuation, ('#pop', 'parenthesis-close', 'type')),
+            default('#pop'),
+        ],
+
+        'abstract-relation': [
+            include('spaces'),
+            (r'(?:to|from)', Keyword.Declaration, 'type'),
+            (r',', Punctuation),
+            default('#pop'),
+        ],
+
+        'meta': [
+            include('spaces'),
+            (r'@', Name.Decorator, ('meta-body', 'meta-ident', 'meta-colon')),
+        ],
+
+        # optional colon
+        'meta-colon': [
+            include('spaces'),
+            (r':', Name.Decorator, '#pop'),
+            default('#pop'),
+        ],
+
+        # same as 'ident' but set token as Name.Decorator instead of Name
+        'meta-ident': [
+            include('spaces'),
+            (ident, Name.Decorator, '#pop'),
+        ],
+
+        'meta-body': [
+            include('spaces'),
+            (r'\(', Name.Decorator, ('#pop', 'meta-call')),
+            default('#pop'),
+        ],
+
+        'meta-call': [
+            include('spaces'),
+            (r'\)', Name.Decorator, '#pop'),
+            default(('#pop', 'meta-call-sep', 'expr')),
+        ],
+
+        'meta-call-sep': [
+            include('spaces'),
+            (r'\)', Name.Decorator, '#pop'),
+            (r',', Punctuation, ('#pop', 'meta-call')),
+        ],
+
+        'typedef': [
+            include('spaces'),
+            default(('#pop', 'typedef-body', 'type-param-constraint',
+                     'type-name')),
+        ],
+
+        'typedef-body': [
+            include('spaces'),
+            (r'=', Operator, ('#pop', 'optional-semicolon', 'type')),
+        ],
+
+        'enum': [
+            include('spaces'),
+            default(('#pop', 'enum-body', 'bracket-open',
+                     'type-param-constraint', 'type-name')),
+        ],
+
+        'enum-body': [
+            include('spaces'),
+            include('meta'),
+            (r'\}', Punctuation, '#pop'),
+            (ident_no_keyword, Name, ('enum-member', 'type-param-constraint')),
+        ],
+
+        'enum-member': [
+            include('spaces'),
+            (r'\(', Punctuation,
+             ('#pop', 'semicolon', 'flag', 'function-param')),
+            default(('#pop', 'semicolon', 'flag')),
+        ],
+
+        'class': [
+            include('spaces'),
+            default(('#pop', 'class-body', 'bracket-open', 'extends',
+                     'type-param-constraint', 'type-name')),
+        ],
+
+        'extends': [
+            include('spaces'),
+            (r'(?:extends|implements)\b', Keyword.Declaration, 'type'),
+            (r',', Punctuation),  # the comma is made optional here, since haxe2
+                                  # requires the comma but haxe3 does not allow it
+            default('#pop'),
+        ],
+
+        'bracket-open': [
+            include('spaces'),
+            (r'\{', Punctuation, '#pop'),
+        ],
+
+        'bracket-close': [
+            include('spaces'),
+            (r'\}', Punctuation, '#pop'),
+        ],
+
+        'class-body': [
+            include('spaces'),
+            include('meta'),
+            (r'\}', Punctuation, '#pop'),
+            (r'(?:static|public|private|override|dynamic|inline|macro)\b',
+             Keyword.Declaration),
+            default('class-member'),
+        ],
+
+        'class-member': [
+            include('spaces'),
+            (r'(var)\b', Keyword.Declaration,
+             ('#pop', 'optional-semicolon', 'var')),
+            (r'(function)\b', Keyword.Declaration,
+             ('#pop', 'optional-semicolon', 'class-method')),
+        ],
+
+        # local function, anonymous or not
+        'function-local': [
+            include('spaces'),
+            (ident_no_keyword, Name.Function,
+             ('#pop', 'optional-expr', 'flag', 'function-param',
+              'parenthesis-open', 'type-param-constraint')),
+            default(('#pop', 'optional-expr', 'flag', 'function-param',
+                     'parenthesis-open', 'type-param-constraint')),
+        ],
+
+        'optional-expr': [
+            include('spaces'),
+            include('expr'),
+            default('#pop'),
+        ],
+
+        'class-method': [
+            include('spaces'),
+            (ident, Name.Function, ('#pop', 'optional-expr', 'flag',
+                                    'function-param', 'parenthesis-open',
+                                    'type-param-constraint')),
+        ],
+
+        # function arguments
+        'function-param': [
+            include('spaces'),
+            (r'\)', Punctuation, '#pop'),
+            (r'\?', Punctuation),
+            (ident_no_keyword, Name,
+             ('#pop', 'function-param-sep', 'assign', 'flag')),
+        ],
+
+        'function-param-sep': [
+            include('spaces'),
+            (r'\)', Punctuation, '#pop'),
+            (r',', Punctuation, ('#pop', 'function-param')),
+        ],
+
+        'prop-get-set': [
+            include('spaces'),
+            (r'\(', Punctuation, ('#pop', 'parenthesis-close',
+                                  'prop-get-set-opt', 'comma', 'prop-get-set-opt')),
+            default('#pop'),
+        ],
+
+        'prop-get-set-opt': [
+            include('spaces'),
+            (r'(?:default|null|never|dynamic|get|set)\b', Keyword, '#pop'),
+            (ident_no_keyword, Text, '#pop'),  # custom getter/setter
+        ],
+
+        'expr-statement': [
+            include('spaces'),
+            # makes semicolon optional here, just to avoid checking the last
+            # one is bracket or not.
+            default(('#pop', 'optional-semicolon', 'expr')),
+        ],
+
+        'expr': [
+            include('spaces'),
+            (r'@', Name.Decorator, ('#pop', 'optional-expr', 'meta-body',
+                                    'meta-ident', 'meta-colon')),
+            (r'(?:\+\+|\-\-|~(?!/)|!|\-)', Operator),
+            (r'\(', Punctuation, ('#pop', 'expr-chain', 'parenthesis')),
+            (r'(?:static|public|private|override|dynamic|inline)\b',
+             Keyword.Declaration),
+            (r'(?:function)\b', Keyword.Declaration, ('#pop', 'expr-chain',
+                                                      'function-local')),
+            (r'\{', Punctuation, ('#pop', 'expr-chain', 'bracket')),
+            (r'(?:true|false|null)\b', Keyword.Constant, ('#pop', 'expr-chain')),
+            (r'(?:this)\b', Keyword, ('#pop', 'expr-chain')),
+            (r'(?:cast)\b', Keyword, ('#pop', 'expr-chain', 'cast')),
+            (r'(?:try)\b', Keyword, ('#pop', 'catch', 'expr')),
+            (r'(?:var)\b', Keyword.Declaration, ('#pop', 'var')),
+            (r'(?:new)\b', Keyword, ('#pop', 'expr-chain', 'new')),
+            (r'(?:switch)\b', Keyword, ('#pop', 'switch')),
+            (r'(?:if)\b', Keyword, ('#pop', 'if')),
+            (r'(?:do)\b', Keyword, ('#pop', 'do')),
+            (r'(?:while)\b', Keyword, ('#pop', 'while')),
+            (r'(?:for)\b', Keyword, ('#pop', 'for')),
+            (r'(?:untyped|throw)\b', Keyword),
+            (r'(?:return)\b', Keyword, ('#pop', 'optional-expr')),
+            (r'(?:macro)\b', Keyword, ('#pop', 'macro')),
+            (r'(?:continue|break)\b', Keyword, '#pop'),
+            (r'(?:\$\s*[a-z]\b|\$(?!'+ident+'))', Name, ('#pop', 'dollar')),
+            (ident_no_keyword, Name, ('#pop', 'expr-chain')),
+
+            # Float
+            (r'\.[0-9]+', Number.Float, ('#pop', 'expr-chain')),
+            (r'[0-9]+[eE][+\-]?[0-9]+', Number.Float, ('#pop', 'expr-chain')),
+            (r'[0-9]+\.[0-9]*[eE][+\-]?[0-9]+', Number.Float, ('#pop', 'expr-chain')),
+            (r'[0-9]+\.[0-9]+', Number.Float, ('#pop', 'expr-chain')),
+            (r'[0-9]+\.(?!' + ident + r'|\.\.)', Number.Float, ('#pop', 'expr-chain')),
+
+            # Int
+            (r'0x[0-9a-fA-F]+', Number.Hex, ('#pop', 'expr-chain')),
+            (r'[0-9]+', Number.Integer, ('#pop', 'expr-chain')),
+
+            # String
+            (r"'", String.Single, ('#pop', 'expr-chain', 'string-single-interpol')),
+            (r'"', String.Double, ('#pop', 'expr-chain', 'string-double')),
+
+            # EReg
+            (r'~/(\\\\|\\[^\\]|[^/\\\n])*/[gimsu]*', String.Regex, ('#pop', 'expr-chain')),
+
+            # Array
+            (r'\[', Punctuation, ('#pop', 'expr-chain', 'array-decl')),
+        ],
+
+        'expr-chain': [
+            include('spaces'),
+            (r'(?:\+\+|\-\-)', Operator),
+            (binop, Operator, ('#pop', 'expr')),
+            (r'(?:in)\b', Keyword, ('#pop', 'expr')),
+            (r'\?', Operator, ('#pop', 'expr', 'ternary', 'expr')),
+            (r'(\.)(' + ident_no_keyword + ')', bygroups(Punctuation, Name)),
+            (r'\[', Punctuation, 'array-access'),
+            (r'\(', Punctuation, 'call'),
+            default('#pop'),
+        ],
+
+        # macro reification
+        'macro': [
+            include('spaces'),
+            include('meta'),
+            (r':', Punctuation, ('#pop', 'type')),
+
+            (r'(?:extern|private)\b', Keyword.Declaration),
+            (r'(?:abstract)\b', Keyword.Declaration, ('#pop', 'optional-semicolon', 'abstract')),
+            (r'(?:class|interface)\b', Keyword.Declaration, ('#pop', 'optional-semicolon', 'macro-class')),
+            (r'(?:enum)\b', Keyword.Declaration, ('#pop', 'optional-semicolon', 'enum')),
+            (r'(?:typedef)\b', Keyword.Declaration, ('#pop', 'optional-semicolon', 'typedef')),
+
+            default(('#pop', 'expr')),
+        ],
+
+        'macro-class': [
+            (r'\{', Punctuation, ('#pop', 'class-body')),
+            include('class')
+        ],
+
+        # cast can be written as "cast expr" or "cast(expr, type)"
+        'cast': [
+            include('spaces'),
+            (r'\(', Punctuation, ('#pop', 'parenthesis-close',
+                                  'cast-type', 'expr')),
+            default(('#pop', 'expr')),
+        ],
+
+        # optionally give a type as the 2nd argument of cast()
+        'cast-type': [
+            include('spaces'),
+            (r',', Punctuation, ('#pop', 'type')),
+            default('#pop'),
+        ],
+
+        'catch': [
+            include('spaces'),
+            (r'(?:catch)\b', Keyword, ('expr', 'function-param',
+                                       'parenthesis-open')),
+            default('#pop'),
+        ],
+
+        # do-while loop
+        'do': [
+            include('spaces'),
+            default(('#pop', 'do-while', 'expr')),
+        ],
+
+        # the while after do
+        'do-while': [
+            include('spaces'),
+            (r'(?:while)\b', Keyword, ('#pop', 'parenthesis',
+                                       'parenthesis-open')),
+        ],
+
+        'while': [
+            include('spaces'),
+            (r'\(', Punctuation, ('#pop', 'expr', 'parenthesis')),
+        ],
+
+        'for': [
+            include('spaces'),
+            (r'\(', Punctuation, ('#pop', 'expr', 'parenthesis')),
+        ],
+
+        'if': [
+            include('spaces'),
+            (r'\(', Punctuation, ('#pop', 'else', 'optional-semicolon', 'expr',
+                                  'parenthesis')),
+        ],
+
+        'else': [
+            include('spaces'),
+            (r'(?:else)\b', Keyword, ('#pop', 'expr')),
+            default('#pop'),
+        ],
+
+        'switch': [
+            include('spaces'),
+            default(('#pop', 'switch-body', 'bracket-open', 'expr')),
+        ],
+
+        'switch-body': [
+            include('spaces'),
+            (r'(?:case|default)\b', Keyword, ('case-block', 'case')),
+            (r'\}', Punctuation, '#pop'),
+        ],
+
+        'case': [
+            include('spaces'),
+            (r':', Punctuation, '#pop'),
+            default(('#pop', 'case-sep', 'case-guard', 'expr')),
+        ],
+
+        'case-sep': [
+            include('spaces'),
+            (r':', Punctuation, '#pop'),
+            (r',', Punctuation, ('#pop', 'case')),
+        ],
+
+        'case-guard': [
+            include('spaces'),
+            (r'(?:if)\b', Keyword, ('#pop', 'parenthesis', 'parenthesis-open')),
+            default('#pop'),
+        ],
+
+        # optional multiple expr under a case
+        'case-block': [
+            include('spaces'),
+            (r'(?!(?:case|default)\b|\})', Keyword, 'expr-statement'),
+            default('#pop'),
+        ],
+
+        'new': [
+            include('spaces'),
+            default(('#pop', 'call', 'parenthesis-open', 'type')),
+        ],
+
+        'array-decl': [
+            include('spaces'),
+            (r'\]', Punctuation, '#pop'),
+            default(('#pop', 'array-decl-sep', 'expr')),
+        ],
+
+        'array-decl-sep': [
+            include('spaces'),
+            (r'\]', Punctuation, '#pop'),
+            (r',', Punctuation, ('#pop', 'array-decl')),
+        ],
+
+        'array-access': [
+            include('spaces'),
+            default(('#pop', 'array-access-close', 'expr')),
+        ],
+
+        'array-access-close': [
+            include('spaces'),
+            (r'\]', Punctuation, '#pop'),
+        ],
+
+        'comma': [
+            include('spaces'),
+            (r',', Punctuation, '#pop'),
+        ],
+
+        'colon': [
+            include('spaces'),
+            (r':', Punctuation, '#pop'),
+        ],
+
+        'semicolon': [
+            include('spaces'),
+            (r';', Punctuation, '#pop'),
+        ],
+
+        'optional-semicolon': [
+            include('spaces'),
+            (r';', Punctuation, '#pop'),
+            default('#pop'),
+        ],
+
+        # identity that CAN be a Haxe keyword
+        'ident': [
+            include('spaces'),
+            (ident, Name, '#pop'),
+        ],
+
+        'dollar': [
+            include('spaces'),
+            (r'\{', Punctuation, ('#pop', 'expr-chain', 'bracket-close', 'expr')),
+            default(('#pop', 'expr-chain')),
+        ],
+
+        'type-name': [
+            include('spaces'),
+            (typeid, Name, '#pop'),
+        ],
+
+        'type-full-name': [
+            include('spaces'),
+            (r'\.', Punctuation, 'ident'),
+            default('#pop'),
+        ],
+
+        'type': [
+            include('spaces'),
+            (r'\?', Punctuation),
+            (ident, Name, ('#pop', 'type-check', 'type-full-name')),
+            (r'\{', Punctuation, ('#pop', 'type-check', 'type-struct')),
+            (r'\(', Punctuation, ('#pop', 'type-check', 'type-parenthesis')),
+        ],
+
+        'type-parenthesis': [
+            include('spaces'),
+            default(('#pop', 'parenthesis-close', 'type')),
+        ],
+
+        'type-check': [
+            include('spaces'),
+            (r'->', Punctuation, ('#pop', 'type')),
+            (r'<(?!=)', Punctuation, 'type-param'),
+            default('#pop'),
+        ],
+
+        'type-struct': [
+            include('spaces'),
+            (r'\}', Punctuation, '#pop'),
+            (r'\?', Punctuation),
+            (r'>', Punctuation, ('comma', 'type')),
+            (ident_no_keyword, Name, ('#pop', 'type-struct-sep', 'type', 'colon')),
+            include('class-body'),
+        ],
+
+        'type-struct-sep': [
+            include('spaces'),
+            (r'\}', Punctuation, '#pop'),
+            (r',', Punctuation, ('#pop', 'type-struct')),
+        ],
+
+        # type-param can be a normal type or a constant literal...
+        'type-param-type': [
+            # Float
+            (r'\.[0-9]+', Number.Float, '#pop'),
+            (r'[0-9]+[eE][+\-]?[0-9]+', Number.Float, '#pop'),
+            (r'[0-9]+\.[0-9]*[eE][+\-]?[0-9]+', Number.Float, '#pop'),
+            (r'[0-9]+\.[0-9]+', Number.Float, '#pop'),
+            (r'[0-9]+\.(?!' + ident + r'|\.\.)', Number.Float, '#pop'),
+
+            # Int
+            (r'0x[0-9a-fA-F]+', Number.Hex, '#pop'),
+            (r'[0-9]+', Number.Integer, '#pop'),
+
+            # String
+            (r"'", String.Single, ('#pop', 'string-single')),
+            (r'"', String.Double, ('#pop', 'string-double')),
+
+            # EReg
+            (r'~/(\\\\|\\[^\\]|[^/\\\n])*/[gim]*', String.Regex, '#pop'),
+
+            # Array
+            (r'\[', Operator, ('#pop', 'array-decl')),
+
+            include('type'),
+        ],
+
+        # type-param part of a type
+        # ie. the <A,B> path in Map<A,B>
+        'type-param': [
+            include('spaces'),
+            default(('#pop', 'type-param-sep', 'type-param-type')),
+        ],
+
+        'type-param-sep': [
+            include('spaces'),
+            (r'>', Punctuation, '#pop'),
+            (r',', Punctuation, ('#pop', 'type-param')),
+        ],
+
+        # optional type-param that may include constraint
+        # ie. <T:Constraint, T2:(ConstraintA,ConstraintB)>
+        'type-param-constraint': [
+            include('spaces'),
+            (r'<(?!=)', Punctuation, ('#pop', 'type-param-constraint-sep',
+                                      'type-param-constraint-flag', 'type-name')),
+            default('#pop'),
+        ],
+
+        'type-param-constraint-sep': [
+            include('spaces'),
+            (r'>', Punctuation, '#pop'),
+            (r',', Punctuation, ('#pop', 'type-param-constraint-sep',
+                                 'type-param-constraint-flag', 'type-name')),
+        ],
+
+        # the optional constraint inside type-param
+        'type-param-constraint-flag': [
+            include('spaces'),
+            (r':', Punctuation, ('#pop', 'type-param-constraint-flag-type')),
+            default('#pop'),
+        ],
+
+        'type-param-constraint-flag-type': [
+            include('spaces'),
+            (r'\(', Punctuation, ('#pop', 'type-param-constraint-flag-type-sep',
+                                  'type')),
+            default(('#pop', 'type')),
+        ],
+
+        'type-param-constraint-flag-type-sep': [
+            include('spaces'),
+            (r'\)', Punctuation, '#pop'),
+            (r',', Punctuation, 'type'),
+        ],
+
+        # a parenthesis expr that contain exactly one expr
+        'parenthesis': [
+            include('spaces'),
+            default(('#pop', 'parenthesis-close', 'flag', 'expr')),
+        ],
+
+        'parenthesis-open': [
+            include('spaces'),
+            (r'\(', Punctuation, '#pop'),
+        ],
+
+        'parenthesis-close': [
+            include('spaces'),
+            (r'\)', Punctuation, '#pop'),
+        ],
+
+        'var': [
+            include('spaces'),
+            (ident_no_keyword, Text, ('#pop', 'var-sep', 'assign', 'flag', 'prop-get-set')),
+        ],
+
+        # optional more var decl.
+        'var-sep': [
+            include('spaces'),
+            (r',', Punctuation, ('#pop', 'var')),
+            default('#pop'),
+        ],
+
+        # optional assignment
+        'assign': [
+            include('spaces'),
+            (r'=', Operator, ('#pop', 'expr')),
+            default('#pop'),
+        ],
+
+        # optional type flag
+        'flag': [
+            include('spaces'),
+            (r':', Punctuation, ('#pop', 'type')),
+            default('#pop'),
+        ],
+
+        # colon as part of a ternary operator (?:)
+        'ternary': [
+            include('spaces'),
+            (r':', Operator, '#pop'),
+        ],
+
+        # function call
+        'call': [
+            include('spaces'),
+            (r'\)', Punctuation, '#pop'),
+            default(('#pop', 'call-sep', 'expr')),
+        ],
+
+        # after a call param
+        'call-sep': [
+            include('spaces'),
+            (r'\)', Punctuation, '#pop'),
+            (r',', Punctuation, ('#pop', 'call')),
+        ],
+
+        # bracket can be block or object
+        'bracket': [
+            include('spaces'),
+            (r'(?!(?:\$\s*[a-z]\b|\$(?!'+ident+')))' + ident_no_keyword, Name,
+             ('#pop', 'bracket-check')),
+            (r"'", String.Single, ('#pop', 'bracket-check', 'string-single')),
+            (r'"', String.Double, ('#pop', 'bracket-check', 'string-double')),
+            default(('#pop', 'block')),
+        ],
+
+        'bracket-check': [
+            include('spaces'),
+            (r':', Punctuation, ('#pop', 'object-sep', 'expr')),  # is object
+            default(('#pop', 'block', 'optional-semicolon', 'expr-chain')),  # is block
+        ],
+
+        # code block
+        'block': [
+            include('spaces'),
+            (r'\}', Punctuation, '#pop'),
+            default('expr-statement'),
+        ],
+
+        # object in key-value pairs
+        'object': [
+            include('spaces'),
+            (r'\}', Punctuation, '#pop'),
+            default(('#pop', 'object-sep', 'expr', 'colon', 'ident-or-string'))
+        ],
+
+        # a key of an object
+        'ident-or-string': [
+            include('spaces'),
+            (ident_no_keyword, Name, '#pop'),
+            (r"'", String.Single, ('#pop', 'string-single')),
+            (r'"', String.Double, ('#pop', 'string-double')),
+        ],
+
+        # after a key-value pair in object
+        'object-sep': [
+            include('spaces'),
+            (r'\}', Punctuation, '#pop'),
+            (r',', Punctuation, ('#pop', 'object')),
+        ],
+
+
+
+    }
+
+    def analyse_text(text):
+        rv = 0
+        if re.search(r'\bimport\s+haxe\.', text):
+            rv = max(rv, 0.2)
+        if re.search(r'\bStd\.', text):
+            rv = max(rv, 0.1)
+        if re.search(r'\btrace\s*\(', text):
+            rv = max(rv, 0.05)
+        return rv
+
+
+class HxmlLexer(RegexLexer):
+    """
+    Lexer for haXe build files.
+    """
+    name = 'Hxml'
+    url = 'https://haxe.org/manual/compiler-usage-hxml.html'
+    aliases = ['haxeml', 'hxml']
+    filenames = ['*.hxml']
+    version_added = '1.6'
+
+    tokens = {
+        'root': [
+            # Separator
+            (r'(--)(next)', bygroups(Punctuation, Generic.Heading)),
+            # Compiler switches with one dash
+            (r'(-)(prompt|debug|v)', bygroups(Punctuation, Keyword.Keyword)),
+            # Compilerswitches with two dashes
+            (r'(--)(neko-source|flash-strict|flash-use-stage|no-opt|no-traces|'
+             r'no-inline|times|no-output)', bygroups(Punctuation, Keyword)),
+            # Targets and other options that take an argument
+            (r'(-)(cpp|js|neko|x|as3|swf9?|swf-lib|php|xml|main|lib|D|resource|'
+             r'cp|cmd)( +)(.+)',
+             bygroups(Punctuation, Keyword, Whitespace, String)),
+            # Options that take only numerical arguments
+            (r'(-)(swf-version)( +)(\d+)',
+             bygroups(Punctuation, Keyword, Whitespace, Number.Integer)),
+            # An Option that defines the size, the fps and the background
+            # color of an flash movie
+            (r'(-)(swf-header)( +)(\d+)(:)(\d+)(:)(\d+)(:)([A-Fa-f0-9]{6})',
+             bygroups(Punctuation, Keyword, Whitespace, Number.Integer,
+                      Punctuation, Number.Integer, Punctuation, Number.Integer,
+                      Punctuation, Number.Hex)),
+            # options with two dashes that takes arguments
+            (r'(--)(js-namespace|php-front|php-lib|remap|gen-hx-classes)( +)'
+             r'(.+)', bygroups(Punctuation, Keyword, Whitespace, String)),
+            # Single line comment, multiline ones are not allowed.
+            (r'#.*', Comment.Single)
+        ]
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/json5.py

@@ -0,0 +1,83 @@
+"""
+    pygments.lexers.json5
+    ~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for Json5 file format.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import include, RegexLexer, words
+from pygments.token import Comment, Keyword, Name, Number, Punctuation, \
+    String, Whitespace
+
+__all__ = ['Json5Lexer']
+
+
+def string_rules(quote_mark):
+    return [
+        (rf"[^{quote_mark}\\]+", String),
+        (r"\\.", String.Escape),
+        (r"\\", Punctuation),
+        (quote_mark, String, '#pop'),
+    ]
+
+
+def quoted_field_name(quote_mark):
+    return [
+        (rf'([^{quote_mark}\\]|\\.)*{quote_mark}',
+         Name.Variable, ('#pop', 'object_value'))
+    ]
+
+
+class Json5Lexer(RegexLexer):
+    """Lexer for JSON5 data structures."""
+
+    name = 'JSON5'
+    aliases = ['json5']
+    filenames = ['*.json5']
+    url = "https://json5.org"
+    version_added = '2.19'
+    tokens = {
+        '_comments': [
+            (r'(//|#).*\n', Comment.Single),
+            (r'/\*\*([^/]|/(?!\*))*\*/', String.Doc),
+            (r'/\*([^/]|/(?!\*))*\*/', Comment),
+        ],
+        'root': [
+            include('_comments'),
+            (r"'", String, 'singlestring'),
+            (r'"', String, 'doublestring'),
+            (r'[+-]?0[xX][0-9a-fA-F]+', Number.Hex),
+            (r'[+-.]?[0-9]+[.]?[0-9]?([eE][-]?[0-9]+)?', Number.Float),
+            (r'\{', Punctuation, 'object'),
+            (r'\[', Punctuation, 'array'),
+            (words(['false', 'Infinity', '+Infinity', '-Infinity', 'NaN',
+                    'null', 'true',], suffix=r'\b'), Keyword),
+            (r'\s+', Whitespace),
+            (r':', Punctuation),
+        ],
+        'singlestring': string_rules("'"),
+        'doublestring': string_rules('"'),
+        'array': [
+            (r',', Punctuation),
+            (r'\]', Punctuation, '#pop'),
+            include('root'),
+        ],
+        'object': [
+            (r'\s+', Whitespace),
+            (r'\}', Punctuation, '#pop'),
+            (r'\b([^:]+)', Name.Variable, 'object_value'),
+            (r'"', Name.Variable, 'double_field_name'),
+            (r"'", Name.Variable, 'single_field_name'),
+            include('_comments'),
+        ],
+        'double_field_name': quoted_field_name('"'),
+        'single_field_name': quoted_field_name("'"),
+        'object_value': [
+            (r',', Punctuation, '#pop'),
+            (r'\}', Punctuation, '#pop:2'),
+            include('root'),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/ooc.py

@@ -0,0 +1,84 @@
+"""
+    pygments.lexers.ooc
+    ~~~~~~~~~~~~~~~~~~~
+
+    Lexers for the Ooc language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer, bygroups, words
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation
+
+__all__ = ['OocLexer']
+
+
+class OocLexer(RegexLexer):
+    """
+    For Ooc source code
+    """
+    name = 'Ooc'
+    url = 'https://ooc-lang.github.io/'
+    aliases = ['ooc']
+    filenames = ['*.ooc']
+    mimetypes = ['text/x-ooc']
+    version_added = '1.2'
+
+    tokens = {
+        'root': [
+            (words((
+                'class', 'interface', 'implement', 'abstract', 'extends', 'from',
+                'this', 'super', 'new', 'const', 'final', 'static', 'import',
+                'use', 'extern', 'inline', 'proto', 'break', 'continue',
+                'fallthrough', 'operator', 'if', 'else', 'for', 'while', 'do',
+                'switch', 'case', 'as', 'in', 'version', 'return', 'true',
+                'false', 'null'), prefix=r'\b', suffix=r'\b'),
+             Keyword),
+            (r'include\b', Keyword, 'include'),
+            (r'(cover)([ \t]+)(from)([ \t]+)(\w+[*@]?)',
+             bygroups(Keyword, Text, Keyword, Text, Name.Class)),
+            (r'(func)((?:[ \t]|\\\n)+)(~[a-z_]\w*)',
+             bygroups(Keyword, Text, Name.Function)),
+            (r'\bfunc\b', Keyword),
+            # Note: %= not listed on https://ooc-lang.github.io/docs/lang/operators/
+            (r'//.*', Comment),
+            (r'(?s)/\*.*?\*/', Comment.Multiline),
+            (r'(==?|\+=?|-[=>]?|\*=?|/=?|:=|!=?|%=?|\?|>{1,3}=?|<{1,3}=?|\.\.|'
+             r'&&?|\|\|?|\^=?)', Operator),
+            (r'(\.)([ \t]*)([a-z]\w*)', bygroups(Operator, Text,
+                                                 Name.Function)),
+            (r'[A-Z][A-Z0-9_]+', Name.Constant),
+            (r'[A-Z]\w*([@*]|\[[ \t]*\])?', Name.Class),
+
+            (r'([a-z]\w*(?:~[a-z]\w*)?)((?:[ \t]|\\\n)*)(?=\()',
+             bygroups(Name.Function, Text)),
+            (r'[a-z]\w*', Name.Variable),
+
+            # : introduces types
+            (r'[:(){}\[\];,]', Punctuation),
+
+            (r'0x[0-9a-fA-F]+', Number.Hex),
+            (r'0c[0-9]+', Number.Oct),
+            (r'0b[01]+', Number.Bin),
+            (r'[0-9_]\.[0-9_]*(?!\.)', Number.Float),
+            (r'[0-9_]+', Number.Decimal),
+
+            (r'"(?:\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\"])*"',
+             String.Double),
+            (r"'(?:\\.|\\[0-9]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])'",
+             String.Char),
+            (r'@', Punctuation),  # pointer dereference
+            (r'\.', Punctuation),  # imports or chain operator
+
+            (r'\\[ \t\n]', Text),
+            (r'[ \t]+', Text),
+        ],
+        'include': [
+            (r'[\w/]+', Name),
+            (r',', Punctuation),
+            (r'[ \t]', Text),
+            (r'[;\n]', Text, '#pop'),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/r.py

@@ -0,0 +1,196 @@
+"""
+    pygments.lexers.r
+    ~~~~~~~~~~~~~~~~~
+
+    Lexers for the R/S languages.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import Lexer, RegexLexer, include, do_insertions
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Generic, Whitespace
+
+__all__ = ['RConsoleLexer', 'SLexer', 'RdLexer']
+
+
+line_re  = re.compile('.*?\n')
+
+
+class RConsoleLexer(Lexer):
+    """
+    For R console transcripts or R CMD BATCH output files.
+    """
+
+    name = 'RConsole'
+    aliases = ['rconsole', 'rout']
+    filenames = ['*.Rout']
+    url = 'https://www.r-project.org'
+    version_added = ''
+    _example = "rconsole/r-console-transcript.Rout"
+
+    def get_tokens_unprocessed(self, text):
+        slexer = SLexer(**self.options)
+
+        current_code_block = ''
+        insertions = []
+
+        for match in line_re.finditer(text):
+            line = match.group()
+            if line.startswith('>') or line.startswith('+'):
+                # Colorize the prompt as such,
+                # then put rest of line into current_code_block
+                insertions.append((len(current_code_block),
+                                   [(0, Generic.Prompt, line[:2])]))
+                current_code_block += line[2:]
+            else:
+                # We have reached a non-prompt line!
+                # If we have stored prompt lines, need to process them first.
+                if current_code_block:
+                    # Weave together the prompts and highlight code.
+                    yield from do_insertions(
+                        insertions, slexer.get_tokens_unprocessed(current_code_block))
+                    # Reset vars for next code block.
+                    current_code_block = ''
+                    insertions = []
+                # Now process the actual line itself, this is output from R.
+                yield match.start(), Generic.Output, line
+
+        # If we happen to end on a code block with nothing after it, need to
+        # process the last code block. This is neither elegant nor DRY so
+        # should be changed.
+        if current_code_block:
+            yield from do_insertions(
+                insertions, slexer.get_tokens_unprocessed(current_code_block))
+
+
+class SLexer(RegexLexer):
+    """
+    For S, S-plus, and R source code.
+    """
+
+    name = 'S'
+    aliases = ['splus', 's', 'r']
+    filenames = ['*.S', '*.R', '.Rhistory', '.Rprofile', '.Renviron']
+    mimetypes = ['text/S-plus', 'text/S', 'text/x-r-source', 'text/x-r',
+                 'text/x-R', 'text/x-r-history', 'text/x-r-profile']
+    url = 'https://www.r-project.org'
+    version_added = '0.10'
+
+    valid_name = r'`[^`\\]*(?:\\.[^`\\]*)*`|(?:[a-zA-Z]|\.[A-Za-z_.])[\w.]*|\.'
+    tokens = {
+        'comments': [
+            (r'#.*$', Comment.Single),
+        ],
+        'valid_name': [
+            (valid_name, Name),
+        ],
+        'function_name': [
+            (rf'({valid_name})\s*(?=\()', Name.Function),
+        ],
+        'punctuation': [
+            (r'\[{1,2}|\]{1,2}|\(|\)|;|,', Punctuation),
+        ],
+        'keywords': [
+            (r'(if|else|for|while|repeat|in|next|break|return|switch|function)'
+             r'(?![\w.])',
+             Keyword.Reserved),
+        ],
+        'operators': [
+            (r'<<?-|->>?|-|==|<=|>=|\|>|<|>|&&?|!=|\|\|?|\?', Operator),
+            (r'\*|\+|\^|/|!|%[^%]*%|=|~|\$|@|:{1,3}', Operator),
+        ],
+        'builtin_symbols': [
+            (r'(NULL|NA(_(integer|real|complex|character)_)?|'
+             r'letters|LETTERS|Inf|TRUE|FALSE|NaN|pi|\.\.(\.|[0-9]+))'
+             r'(?![\w.])',
+             Keyword.Constant),
+            (r'(T|F)\b', Name.Builtin.Pseudo),
+        ],
+        'numbers': [
+            # hex number
+            (r'0[xX][a-fA-F0-9]+([pP][0-9]+)?[Li]?', Number.Hex),
+            # decimal number
+            (r'[+-]?([0-9]+(\.[0-9]+)?|\.[0-9]+|\.)([eE][+-]?[0-9]+)?[Li]?',
+             Number),
+        ],
+        'statements': [
+            include('comments'),
+            # whitespaces
+            (r'\s+', Whitespace),
+            (r'\'', String, 'string_squote'),
+            (r'\"', String, 'string_dquote'),
+            include('builtin_symbols'),
+            include('keywords'),
+            include('function_name'),
+            include('valid_name'),
+            include('numbers'),
+            include('punctuation'),
+            include('operators'),
+        ],
+        'root': [
+            # calls:
+            include('statements'),
+            # blocks:
+            (r'\{|\}', Punctuation),
+            # (r'\{', Punctuation, 'block'),
+            (r'.', Text),
+        ],
+        # 'block': [
+        #    include('statements'),
+        #    ('\{', Punctuation, '#push'),
+        #    ('\}', Punctuation, '#pop')
+        # ],
+        'string_squote': [
+            (r'([^\'\\]|\\.)*\'', String, '#pop'),
+        ],
+        'string_dquote': [
+            (r'([^"\\]|\\.)*"', String, '#pop'),
+        ],
+    }
+
+    def analyse_text(text):
+        if re.search(r'[a-z0-9_\])\s]<-(?!-)', text):
+            return 0.11
+
+
+class RdLexer(RegexLexer):
+    """
+    Pygments Lexer for R documentation (Rd) files
+
+    This is a very minimal implementation, highlighting little more
+    than the macros. A description of Rd syntax is found in `Writing R
+    Extensions <http://cran.r-project.org/doc/manuals/R-exts.html>`_
+    and `Parsing Rd files <http://developer.r-project.org/parseRd.pdf>`_.
+    """
+    name = 'Rd'
+    aliases = ['rd']
+    filenames = ['*.Rd']
+    mimetypes = ['text/x-r-doc']
+    url = 'http://cran.r-project.org/doc/manuals/R-exts.html'
+    version_added = '1.6'
+
+    # To account for verbatim / LaTeX-like / and R-like areas
+    # would require parsing.
+    tokens = {
+        'root': [
+            # catch escaped brackets and percent sign
+            (r'\\[\\{}%]', String.Escape),
+            # comments
+            (r'%.*$', Comment),
+            # special macros with no arguments
+            (r'\\(?:cr|l?dots|R|tab)\b', Keyword.Constant),
+            # macros
+            (r'\\[a-zA-Z]+\b', Keyword),
+            # special preprocessor macros
+            (r'^\s*#(?:ifn?def|endif).*\b', Comment.Preproc),
+            # non-escaped brackets
+            (r'[{}]', Name.Builtin),
+            # everything else
+            (r'[^\\%\n{}]+', Text),
+            (r'.', Text),
+        ]
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/scdoc.py

@@ -0,0 +1,85 @@
+"""
+    pygments.lexers.scdoc
+    ~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for scdoc, a simple man page generator.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, include, bygroups, using, this
+from pygments.token import Text, Comment, Keyword, String, Generic
+
+__all__ = ['ScdocLexer']
+
+
+class ScdocLexer(RegexLexer):
+    """
+    `scdoc` is a simple man page generator for POSIX systems written in C99.
+    """
+    name = 'scdoc'
+    url = 'https://git.sr.ht/~sircmpwn/scdoc'
+    aliases = ['scdoc', 'scd']
+    filenames = ['*.scd', '*.scdoc']
+    version_added = '2.5'
+    flags = re.MULTILINE
+
+    tokens = {
+        'root': [
+            # comment
+            (r'^(;.+\n)', bygroups(Comment)),
+
+            # heading with pound prefix
+            (r'^(#)([^#].+\n)', bygroups(Generic.Heading, Text)),
+            (r'^(#{2})(.+\n)', bygroups(Generic.Subheading, Text)),
+            # bulleted lists
+            (r'^(\s*)([*-])(\s)(.+\n)',
+            bygroups(Text, Keyword, Text, using(this, state='inline'))),
+            # numbered lists
+            (r'^(\s*)(\.+\.)( .+\n)',
+            bygroups(Text, Keyword, using(this, state='inline'))),
+            # quote
+            (r'^(\s*>\s)(.+\n)', bygroups(Keyword, Generic.Emph)),
+            # text block
+            (r'^(```\n)([\w\W]*?)(^```$)', bygroups(String, Text, String)),
+
+            include('inline'),
+        ],
+        'inline': [
+            # escape
+            (r'\\.', Text),
+            # underlines
+            (r'(\s)(_[^_]+_)(\W|\n)', bygroups(Text, Generic.Emph, Text)),
+            # bold
+            (r'(\s)(\*[^*]+\*)(\W|\n)', bygroups(Text, Generic.Strong, Text)),
+            # inline code
+            (r'`[^`]+`', String.Backtick),
+
+            # general text, must come last!
+            (r'[^\\\s]+', Text),
+            (r'.', Text),
+        ],
+    }
+
+    def analyse_text(text):
+        """We checks for bold and underline text with * and _. Also
+        every scdoc file must start with a strictly defined first line."""
+        result = 0
+
+        if '*' in text:
+            result += 0.01
+
+        if '_' in text:
+            result += 0.01
+
+        # name(section) ["left_footer" ["center_header"]]
+        first_line = text.partition('\n')[0]
+        scdoc_preamble_pattern = r'^.*\([1-7]\)( "[^"]+"){0,2}$'
+
+        if re.search(scdoc_preamble_pattern, first_line):
+            result += 0.5
+
+        return result

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/teraterm.py

@@ -0,0 +1,335 @@
+"""
+    pygments.lexers.teraterm
+    ~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexer for Tera Term macro files.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, include, bygroups
+from pygments.token import Text, Comment, Operator, Name, String, \
+    Number, Keyword, Error
+
+__all__ = ['TeraTermLexer']
+
+
+class TeraTermLexer(RegexLexer):
+    """
+    For Tera Term macro source code.
+    """
+    name = 'Tera Term macro'
+    url = 'https://ttssh2.osdn.jp/'
+    aliases = ['teratermmacro', 'teraterm', 'ttl']
+    filenames = ['*.ttl']
+    mimetypes = ['text/x-teratermmacro']
+    version_added = '2.4'
+
+    tokens = {
+        'root': [
+            include('comments'),
+            include('labels'),
+            include('commands'),
+            include('builtin-variables'),
+            include('user-variables'),
+            include('operators'),
+            include('numeric-literals'),
+            include('string-literals'),
+            include('all-whitespace'),
+            (r'\S', Text),
+        ],
+        'comments': [
+            (r';[^\r\n]*', Comment.Single),
+            (r'/\*', Comment.Multiline, 'in-comment'),
+        ],
+        'in-comment': [
+            (r'\*/', Comment.Multiline, '#pop'),
+            (r'[^*/]+', Comment.Multiline),
+            (r'[*/]', Comment.Multiline)
+        ],
+        'labels': [
+            (r'(?i)^(\s*)(:[a-z0-9_]+)', bygroups(Text.Whitespace, Name.Label)),
+        ],
+        'commands': [
+            (
+                r'(?i)\b('
+                r'basename|'
+                r'beep|'
+                r'bplusrecv|'
+                r'bplussend|'
+                r'break|'
+                r'bringupbox|'
+                # 'call' is handled separately.
+                r'callmenu|'
+                r'changedir|'
+                r'checksum16|'
+                r'checksum16file|'
+                r'checksum32|'
+                r'checksum32file|'
+                r'checksum8|'
+                r'checksum8file|'
+                r'clearscreen|'
+                r'clipb2var|'
+                r'closesbox|'
+                r'closett|'
+                r'code2str|'
+                r'connect|'
+                r'continue|'
+                r'crc16|'
+                r'crc16file|'
+                r'crc32|'
+                r'crc32file|'
+                r'cygconnect|'
+                r'delpassword|'
+                r'delpassword2|'
+                r'dirname|'
+                r'dirnamebox|'
+                r'disconnect|'
+                r'dispstr|'
+                r'do|'
+                r'else|'
+                r'elseif|'
+                r'enablekeyb|'
+                r'end|'
+                r'endif|'
+                r'enduntil|'
+                r'endwhile|'
+                r'exec|'
+                r'execcmnd|'
+                r'exit|'
+                r'expandenv|'
+                r'fileclose|'
+                r'fileconcat|'
+                r'filecopy|'
+                r'filecreate|'
+                r'filedelete|'
+                r'filelock|'
+                r'filemarkptr|'
+                r'filenamebox|'
+                r'fileopen|'
+                r'fileread|'
+                r'filereadln|'
+                r'filerename|'
+                r'filesearch|'
+                r'fileseek|'
+                r'fileseekback|'
+                r'filestat|'
+                r'filestrseek|'
+                r'filestrseek2|'
+                r'filetruncate|'
+                r'fileunlock|'
+                r'filewrite|'
+                r'filewriteln|'
+                r'findclose|'
+                r'findfirst|'
+                r'findnext|'
+                r'flushrecv|'
+                r'foldercreate|'
+                r'folderdelete|'
+                r'foldersearch|'
+                r'for|'
+                r'getdate|'
+                r'getdir|'
+                r'getenv|'
+                r'getfileattr|'
+                r'gethostname|'
+                r'getipv4addr|'
+                r'getipv6addr|'
+                r'getmodemstatus|'
+                r'getpassword|'
+                r'getpassword2|'
+                r'getspecialfolder|'
+                r'gettime|'
+                r'gettitle|'
+                r'getttdir|'
+                r'getttpos|'
+                r'getver|'
+                # 'goto' is handled separately.
+                r'if|'
+                r'ifdefined|'
+                r'include|'
+                r'inputbox|'
+                r'int2str|'
+                r'intdim|'
+                r'ispassword|'
+                r'ispassword2|'
+                r'kmtfinish|'
+                r'kmtget|'
+                r'kmtrecv|'
+                r'kmtsend|'
+                r'listbox|'
+                r'loadkeymap|'
+                r'logautoclosemode|'
+                r'logclose|'
+                r'loginfo|'
+                r'logopen|'
+                r'logpause|'
+                r'logrotate|'
+                r'logstart|'
+                r'logwrite|'
+                r'loop|'
+                r'makepath|'
+                r'messagebox|'
+                r'mpause|'
+                r'next|'
+                r'passwordbox|'
+                r'pause|'
+                r'quickvanrecv|'
+                r'quickvansend|'
+                r'random|'
+                r'recvfile'
+                r'recvln|'
+                r'regexoption|'
+                r'restoresetup|'
+                r'return|'
+                r'rotateleft|'
+                r'rotateright|'
+                r'scprecv|'
+                r'scpsend|'
+                r'send|'
+                r'sendbinary|'
+                r'sendbreak|'
+                r'sendbroadcast|'
+                r'sendfile|'
+                r'sendkcode|'
+                r'sendln|'
+                r'sendlnbroadcast|'
+                r'sendlnmulticast|'
+                r'sendmulticast|'
+                r'sendtext|'
+                r'setbaud|'
+                r'setdate|'
+                r'setdebug|'
+                r'setdir|'
+                r'setdlgpos|'
+                r'setdtr|'
+                r'setecho|'
+                r'setenv|'
+                r'setexitcode|'
+                r'setfileattr|'
+                r'setflowctrl|'
+                r'setmulticastname|'
+                r'setpassword|'
+                r'setpassword2|'
+                r'setrts|'
+                r'setserialdelaychar'
+                r'setserialdelayline'
+                r'setspeed|'
+                r'setsync|'
+                r'settime|'
+                r'settitle|'
+                r'show|'
+                r'showtt|'
+                r'sprintf|'
+                r'sprintf2|'
+                r'statusbox|'
+                r'str2code|'
+                r'str2int|'
+                r'strcompare|'
+                r'strconcat|'
+                r'strcopy|'
+                r'strdim|'
+                r'strinsert|'
+                r'strjoin|'
+                r'strlen|'
+                r'strmatch|'
+                r'strremove|'
+                r'strreplace|'
+                r'strscan|'
+                r'strspecial|'
+                r'strsplit|'
+                r'strtrim|'
+                r'testlink|'
+                r'then|'
+                r'tolower|'
+                r'toupper|'
+                r'unlink|'
+                r'until|'
+                r'uptime|'
+                r'var2clipb|'
+                r'wait|'
+                r'wait4all|'
+                r'waitevent|'
+                r'waitln|'
+                r'waitn|'
+                r'waitrecv|'
+                r'waitregex|'
+                r'while|'
+                r'xmodemrecv|'
+                r'xmodemsend|'
+                r'yesnobox|'
+                r'ymodemrecv|'
+                r'ymodemsend|'
+                r'zmodemrecv|'
+                r'zmodemsend'
+                r')\b',
+                Keyword,
+            ),
+            (r'(?i)(call|goto)([ \t]+)([a-z0-9_]+)',
+             bygroups(Keyword, Text.Whitespace, Name.Label)),
+        ],
+        'builtin-variables': [
+            (
+                r'(?i)('
+                r'groupmatchstr1|'
+                r'groupmatchstr2|'
+                r'groupmatchstr3|'
+                r'groupmatchstr4|'
+                r'groupmatchstr5|'
+                r'groupmatchstr6|'
+                r'groupmatchstr7|'
+                r'groupmatchstr8|'
+                r'groupmatchstr9|'
+                r'inputstr|'
+                r'matchstr|'
+                r'mtimeout|'
+                r'param1|'
+                r'param2|'
+                r'param3|'
+                r'param4|'
+                r'param5|'
+                r'param6|'
+                r'param7|'
+                r'param8|'
+                r'param9|'
+                r'paramcnt|'
+                r'params|'
+                r'result|'
+                r'timeout'
+                r')\b',
+                Name.Builtin
+            ),
+        ],
+        'user-variables': [
+            (r'(?i)[a-z_][a-z0-9_]*', Name.Variable),
+        ],
+        'numeric-literals': [
+            (r'(-?)([0-9]+)', bygroups(Operator, Number.Integer)),
+            (r'(?i)\$[0-9a-f]+', Number.Hex),
+        ],
+        'string-literals': [
+            (r'(?i)#(?:[0-9]+|\$[0-9a-f]+)', String.Char),
+            (r"'[^'\n]*'", String.Single),
+            (r'"[^"\n]*"', String.Double),
+            # Opening quotes without a closing quote on the same line are errors.
+            (r"('[^']*)(\n)", bygroups(Error, Text.Whitespace)),
+            (r'("[^"]*)(\n)', bygroups(Error, Text.Whitespace)),
+        ],
+        'operators': [
+            (r'and|not|or|xor', Operator.Word),
+            (r'[!%&*+<=>^~\|\/-]+', Operator),
+            (r'[()]', String.Symbol),
+        ],
+        'all-whitespace': [
+            (r'\s+', Text.Whitespace),
+        ],
+    }
+
+    # Turtle and Tera Term macro files share the same file extension
+    # but each has a recognizable and distinct syntax.
+    def analyse_text(text):
+        if re.search(TeraTermLexer.tokens['commands'][0][0], text):
+            return 0.01

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/tnt.py

@@ -0,0 +1,270 @@
+"""
+    pygments.lexers.tnt
+    ~~~~~~~~~~~~~~~~~~~
+
+    Lexer for Typographic Number Theory.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import Lexer
+from pygments.token import Text, Comment, Operator, Keyword, Name, Number, \
+    Punctuation, Error
+
+__all__ = ['TNTLexer']
+
+
+class TNTLexer(Lexer):
+    """
+    Lexer for Typographic Number Theory, as described in the book
+    Gödel, Escher, Bach, by Douglas R. Hofstadter
+    """
+
+    name = 'Typographic Number Theory'
+    url = 'https://github.com/Kenny2github/language-tnt'
+    aliases = ['tnt']
+    filenames = ['*.tnt']
+    version_added = '2.7'
+
+    cur = []
+
+    LOGIC = set('⊃→]&∧^|∨Vv')
+    OPERATORS = set('+.⋅*')
+    VARIABLES = set('abcde')
+    PRIMES = set("'′")
+    NEGATORS = set('~!')
+    QUANTIFIERS = set('AE∀∃')
+    NUMBERS = set('0123456789')
+    WHITESPACE = set('\t \v\n')
+
+    RULES = re.compile('''(?xi)
+        joining | separation | double-tilde | fantasy\\ rule
+        | carry[- ]over(?:\\ of)?(?:\\ line)?\\ ([0-9]+) | detachment
+        | contrapositive | De\\ Morgan | switcheroo
+        | specification | generalization | interchange
+        | existence | symmetry | transitivity
+        | add\\ S | drop\\ S | induction
+        | axiom\\ ([1-5]) | premise | push | pop
+    ''')
+    LINENOS = re.compile(r'(?:[0-9]+)(?:(?:, ?|,? and )(?:[0-9]+))*')
+    COMMENT = re.compile(r'\[[^\n\]]+\]')
+
+    def __init__(self, *args, **kwargs):
+        Lexer.__init__(self, *args, **kwargs)
+        self.cur = []
+
+    def whitespace(self, start, text, required=False):
+        """Tokenize whitespace."""
+        end = start
+        try:
+            while text[end] in self.WHITESPACE:
+                end += 1
+        except IndexError:
+            end = len(text)
+        if required and end == start:
+            raise AssertionError
+        if end != start:
+            self.cur.append((start, Text, text[start:end]))
+        return end
+
+    def variable(self, start, text):
+        """Tokenize a variable."""
+        if text[start] not in self.VARIABLES:
+            raise AssertionError
+        end = start+1
+        while text[end] in self.PRIMES:
+            end += 1
+        self.cur.append((start, Name.Variable, text[start:end]))
+        return end
+
+    def term(self, start, text):
+        """Tokenize a term."""
+        if text[start] == 'S':  # S...S(...) or S...0
+            end = start+1
+            while text[end] == 'S':
+                end += 1
+            self.cur.append((start, Number.Integer, text[start:end]))
+            return self.term(end, text)
+        if text[start] == '0':  # the singleton 0
+            self.cur.append((start, Number.Integer, text[start]))
+            return start+1
+        if text[start] in self.VARIABLES:  # a''...
+            return self.variable(start, text)
+        if text[start] == '(':  # (...+...)
+            self.cur.append((start, Punctuation, text[start]))
+            start = self.term(start+1, text)
+            if text[start] not in self.OPERATORS:
+                raise AssertionError
+            self.cur.append((start, Operator, text[start]))
+            start = self.term(start+1, text)
+            if text[start] != ')':
+                raise AssertionError
+            self.cur.append((start, Punctuation, text[start]))
+            return start+1
+        raise AssertionError  # no matches
+
+    def formula(self, start, text):
+        """Tokenize a formula."""
+        if text[start] in self.NEGATORS:  # ~<...>
+            end = start+1
+            while text[end] in self.NEGATORS:
+                end += 1
+            self.cur.append((start, Operator, text[start:end]))
+            return self.formula(end, text)
+        if text[start] in self.QUANTIFIERS:  # Aa:<...>
+            self.cur.append((start, Keyword.Declaration, text[start]))
+            start = self.variable(start+1, text)
+            if text[start] != ':':
+                raise AssertionError
+            self.cur.append((start, Punctuation, text[start]))
+            return self.formula(start+1, text)
+        if text[start] == '<':  # <...&...>
+            self.cur.append((start, Punctuation, text[start]))
+            start = self.formula(start+1, text)
+            if text[start] not in self.LOGIC:
+                raise AssertionError
+            self.cur.append((start, Operator, text[start]))
+            start = self.formula(start+1, text)
+            if text[start] != '>':
+                raise AssertionError
+            self.cur.append((start, Punctuation, text[start]))
+            return start+1
+        # ...=...
+        start = self.term(start, text)
+        if text[start] != '=':
+            raise AssertionError
+        self.cur.append((start, Operator, text[start]))
+        start = self.term(start+1, text)
+        return start
+
+    def rule(self, start, text):
+        """Tokenize a rule."""
+        match = self.RULES.match(text, start)
+        if match is None:
+            raise AssertionError
+        groups = sorted(match.regs[1:])  # exclude whole match
+        for group in groups:
+            if group[0] >= 0:  # this group matched
+                self.cur.append((start, Keyword, text[start:group[0]]))
+                self.cur.append((group[0], Number.Integer,
+                                 text[group[0]:group[1]]))
+                if group[1] != match.end():
+                    self.cur.append((group[1], Keyword,
+                                     text[group[1]:match.end()]))
+                break
+        else:
+            self.cur.append((start, Keyword, text[start:match.end()]))
+        return match.end()
+
+    def lineno(self, start, text):
+        """Tokenize a line referral."""
+        end = start
+        while text[end] not in self.NUMBERS:
+            end += 1
+        self.cur.append((start, Punctuation, text[start]))
+        self.cur.append((start+1, Text, text[start+1:end]))
+        start = end
+        match = self.LINENOS.match(text, start)
+        if match is None:
+            raise AssertionError
+        if text[match.end()] != ')':
+            raise AssertionError
+        self.cur.append((match.start(), Number.Integer, match.group(0)))
+        self.cur.append((match.end(), Punctuation, text[match.end()]))
+        return match.end() + 1
+
+    def error_till_line_end(self, start, text):
+        """Mark everything from ``start`` to the end of the line as Error."""
+        end = start
+        try:
+            while text[end] != '\n':  # there's whitespace in rules
+                end += 1
+        except IndexError:
+            end = len(text)
+        if end != start:
+            self.cur.append((start, Error, text[start:end]))
+        end = self.whitespace(end, text)
+        return end
+
+    def get_tokens_unprocessed(self, text):
+        """Returns a list of TNT tokens."""
+        self.cur = []
+        start = end = self.whitespace(0, text)
+        while start <= end < len(text):
+            try:
+                # try line number
+                while text[end] in self.NUMBERS:
+                    end += 1
+                if end != start:  # actual number present
+                    self.cur.append((start, Number.Integer, text[start:end]))
+                    # whitespace is required after a line number
+                    orig = len(self.cur)
+                    try:
+                        start = end = self.whitespace(end, text, True)
+                    except AssertionError:
+                        del self.cur[orig:]
+                        start = end = self.error_till_line_end(end, text)
+                        continue
+                # at this point it could be a comment
+                match = self.COMMENT.match(text, start)
+                if match is not None:
+                    self.cur.append((start, Comment, text[start:match.end()]))
+                    start = end = match.end()
+                    # anything after the closing bracket is invalid
+                    start = end = self.error_till_line_end(start, text)
+                    # do not attempt to process the rest
+                    continue
+                del match
+                if text[start] in '[]':  # fantasy push or pop
+                    self.cur.append((start, Keyword, text[start]))
+                    start += 1
+                    end += 1
+                else:
+                    # one formula, possibly containing subformulae
+                    orig = len(self.cur)
+                    try:
+                        start = end = self.formula(start, text)
+                    except (AssertionError, RecursionError):  # not well-formed
+                        del self.cur[orig:]
+                        while text[end] not in self.WHITESPACE:
+                            end += 1
+                        self.cur.append((start, Error, text[start:end]))
+                        start = end
+                # skip whitespace after formula
+                orig = len(self.cur)
+                try:
+                    start = end = self.whitespace(end, text, True)
+                except AssertionError:
+                    del self.cur[orig:]
+                    start = end = self.error_till_line_end(start, text)
+                    continue
+                # rule proving this formula a theorem
+                orig = len(self.cur)
+                try:
+                    start = end = self.rule(start, text)
+                except AssertionError:
+                    del self.cur[orig:]
+                    start = end = self.error_till_line_end(start, text)
+                    continue
+                # skip whitespace after rule
+                start = end = self.whitespace(end, text)
+                # line marker
+                if text[start] == '(':
+                    orig = len(self.cur)
+                    try:
+                        start = end = self.lineno(start, text)
+                    except AssertionError:
+                        del self.cur[orig:]
+                        start = end = self.error_till_line_end(start, text)
+                        continue
+                    start = end = self.whitespace(start, text)
+            except IndexError:
+                try:
+                    del self.cur[orig:]
+                except NameError:
+                    pass  # if orig was never defined, fine
+                self.error_till_line_end(start, text)
+        return self.cur

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/urbi.py

@@ -0,0 +1,145 @@
+"""
+    pygments.lexers.urbi
+    ~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for UrbiScript language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import ExtendedRegexLexer, words
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation
+
+__all__ = ['UrbiscriptLexer']
+
+
+class UrbiscriptLexer(ExtendedRegexLexer):
+    """
+    For UrbiScript source code.
+    """
+
+    name = 'UrbiScript'
+    aliases = ['urbiscript']
+    filenames = ['*.u']
+    mimetypes = ['application/x-urbiscript']
+    url = 'https://github.com/urbiforge/urbi'
+    version_added = '1.5'
+
+    flags = re.DOTALL
+
+    # TODO
+    # - handle Experimental and deprecated tags with specific tokens
+    # - handle Angles and Durations with specific tokens
+
+    def blob_callback(lexer, match, ctx):
+        text_before_blob = match.group(1)
+        blob_start = match.group(2)
+        blob_size_str = match.group(3)
+        blob_size = int(blob_size_str)
+        yield match.start(), String, text_before_blob
+        ctx.pos += len(text_before_blob)
+
+        # if blob size doesn't match blob format (example : "\B(2)(aaa)")
+        # yield blob as a string
+        if ctx.text[match.end() + blob_size] != ")":
+            result = "\\B(" + blob_size_str + ")("
+            yield match.start(), String, result
+            ctx.pos += len(result)
+            return
+
+        # if blob is well formatted, yield as Escape
+        blob_text = blob_start + ctx.text[match.end():match.end()+blob_size] + ")"
+        yield match.start(), String.Escape, blob_text
+        ctx.pos = match.end() + blob_size + 1  # +1 is the ending ")"
+
+    tokens = {
+        'root': [
+            (r'\s+', Text),
+            # comments
+            (r'//.*?\n', Comment),
+            (r'/\*', Comment.Multiline, 'comment'),
+            (r'(every|for|loop|while)(?:;|&|\||,)', Keyword),
+            (words((
+                'assert', 'at', 'break', 'case', 'catch', 'closure', 'compl',
+                'continue', 'default', 'else', 'enum', 'every', 'external',
+                'finally', 'for', 'freezeif', 'if', 'new', 'onleave', 'return',
+                'stopif', 'switch', 'this', 'throw', 'timeout', 'try',
+                'waituntil', 'whenever', 'while'), suffix=r'\b'),
+             Keyword),
+            (words((
+                'asm', 'auto', 'bool', 'char', 'const_cast', 'delete', 'double',
+                'dynamic_cast', 'explicit', 'export', 'extern', 'float', 'friend',
+                'goto', 'inline', 'int', 'long', 'mutable', 'namespace', 'register',
+                'reinterpret_cast', 'short', 'signed', 'sizeof', 'static_cast',
+                'struct', 'template', 'typedef', 'typeid', 'typename', 'union',
+                'unsigned', 'using', 'virtual', 'volatile', 'wchar_t'), suffix=r'\b'),
+             Keyword.Reserved),
+            # deprecated keywords, use a meaningful token when available
+            (r'(emit|foreach|internal|loopn|static)\b', Keyword),
+            # ignored keywords, use a meaningful token when available
+            (r'(private|protected|public)\b', Keyword),
+            (r'(var|do|const|function|class)\b', Keyword.Declaration),
+            (r'(true|false|nil|void)\b', Keyword.Constant),
+            (words((
+                'Barrier', 'Binary', 'Boolean', 'CallMessage', 'Channel', 'Code',
+                'Comparable', 'Container', 'Control', 'Date', 'Dictionary', 'Directory',
+                'Duration', 'Enumeration', 'Event', 'Exception', 'Executable', 'File',
+                'Finalizable', 'Float', 'FormatInfo', 'Formatter', 'Global', 'Group',
+                'Hash', 'InputStream', 'IoService', 'Job', 'Kernel', 'Lazy', 'List',
+                'Loadable', 'Lobby', 'Location', 'Logger', 'Math', 'Mutex', 'nil',
+                'Object', 'Orderable', 'OutputStream', 'Pair', 'Path', 'Pattern',
+                'Position', 'Primitive', 'Process', 'Profile', 'PseudoLazy', 'PubSub',
+                'RangeIterable', 'Regexp', 'Semaphore', 'Server', 'Singleton', 'Socket',
+                'StackFrame', 'Stream', 'String', 'System', 'Tag', 'Timeout',
+                'Traceable', 'TrajectoryGenerator', 'Triplet', 'Tuple', 'UObject',
+                'UValue', 'UVar'), suffix=r'\b'),
+             Name.Builtin),
+            (r'(?:this)\b', Name.Builtin.Pseudo),
+            # don't match single | and &
+            (r'(?:[-=+*%/<>~^:]+|\.&?|\|\||&&)', Operator),
+            (r'(?:and_eq|and|bitand|bitor|in|not|not_eq|or_eq|or|xor_eq|xor)\b',
+             Operator.Word),
+            (r'[{}\[\]()]+', Punctuation),
+            (r'(?:;|\||,|&|\?|!)+', Punctuation),
+            (r'[$a-zA-Z_]\w*', Name.Other),
+            (r'0x[0-9a-fA-F]+', Number.Hex),
+            # Float, Integer, Angle and Duration
+            (r'(?:[0-9]+(?:(?:\.[0-9]+)?(?:[eE][+-]?[0-9]+)?)?'
+             r'((?:rad|deg|grad)|(?:ms|s|min|h|d))?)\b', Number.Float),
+            # handle binary blob in strings
+            (r'"', String.Double, "string.double"),
+            (r"'", String.Single, "string.single"),
+        ],
+        'string.double': [
+            (r'((?:\\\\|\\"|[^"])*?)(\\B\((\d+)\)\()', blob_callback),
+            (r'(\\\\|\\[^\\]|[^"\\])*?"', String.Double, '#pop'),
+        ],
+        'string.single': [
+            (r"((?:\\\\|\\'|[^'])*?)(\\B\((\d+)\)\()", blob_callback),
+            (r"(\\\\|\\[^\\]|[^'\\])*?'", String.Single, '#pop'),
+        ],
+        # from http://pygments.org/docs/lexerdevelopment/#changing-states
+        'comment': [
+            (r'[^*/]', Comment.Multiline),
+            (r'/\*', Comment.Multiline, '#push'),
+            (r'\*/', Comment.Multiline, '#pop'),
+            (r'[*/]', Comment.Multiline),
+        ]
+    }
+
+    def analyse_text(text):
+        """This is fairly similar to C and others, but freezeif and
+        waituntil are unique keywords."""
+        result = 0
+
+        if 'freezeif' in text:
+            result += 0.05
+
+        if 'waituntil' in text:
+            result += 0.05
+
+        return result

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/webmisc.py

@@ -0,0 +1,1006 @@
+"""
+    pygments.lexers.webmisc
+    ~~~~~~~~~~~~~~~~~~~~~~~
+
+    Lexers for misc. web stuff.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+import re
+
+from pygments.lexer import RegexLexer, ExtendedRegexLexer, include, bygroups, \
+    default, using
+from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
+    Number, Punctuation, Literal, Whitespace
+
+from pygments.lexers.css import _indentation, _starts_block
+from pygments.lexers.html import HtmlLexer
+from pygments.lexers.javascript import JavascriptLexer
+from pygments.lexers.ruby import RubyLexer
+
+__all__ = ['DuelLexer', 'SlimLexer', 'XQueryLexer', 'QmlLexer', 'CirruLexer']
+
+
+class DuelLexer(RegexLexer):
+    """
+    Lexer for Duel Views Engine (formerly JBST) markup with JavaScript code blocks.
+    """
+
+    name = 'Duel'
+    url = 'http://duelengine.org/'
+    aliases = ['duel', 'jbst', 'jsonml+bst']
+    filenames = ['*.duel', '*.jbst']
+    mimetypes = ['text/x-duel', 'text/x-jbst']
+    version_added = '1.4'
+
+    flags = re.DOTALL
+
+    tokens = {
+        'root': [
+            (r'(<%[@=#!:]?)(.*?)(%>)',
+             bygroups(Name.Tag, using(JavascriptLexer), Name.Tag)),
+            (r'(<%\$)(.*?)(:)(.*?)(%>)',
+             bygroups(Name.Tag, Name.Function, Punctuation, String, Name.Tag)),
+            (r'(<%--)(.*?)(--%>)',
+             bygroups(Name.Tag, Comment.Multiline, Name.Tag)),
+            (r'(<script.*?>)(.*?)(</script>)',
+             bygroups(using(HtmlLexer),
+                      using(JavascriptLexer), using(HtmlLexer))),
+            (r'(.+?)(?=<)', using(HtmlLexer)),
+            (r'.+', using(HtmlLexer)),
+        ],
+    }
+
+
+class XQueryLexer(ExtendedRegexLexer):
+    """
+    An XQuery lexer, parsing a stream and outputting the tokens needed to
+    highlight xquery code.
+    """
+    name = 'XQuery'
+    url = 'https://www.w3.org/XML/Query/'
+    aliases = ['xquery', 'xqy', 'xq', 'xql', 'xqm']
+    filenames = ['*.xqy', '*.xquery', '*.xq', '*.xql', '*.xqm']
+    mimetypes = ['text/xquery', 'application/xquery']
+    version_added = '1.4'
+
+    xquery_parse_state = []
+
+    # FIX UNICODE LATER
+    # ncnamestartchar = (
+    #    r"[A-Z]|_|[a-z]|[\u00C0-\u00D6]|[\u00D8-\u00F6]|[\u00F8-\u02FF]|"
+    #    r"[\u0370-\u037D]|[\u037F-\u1FFF]|[\u200C-\u200D]|[\u2070-\u218F]|"
+    #    r"[\u2C00-\u2FEF]|[\u3001-\uD7FF]|[\uF900-\uFDCF]|[\uFDF0-\uFFFD]|"
+    #    r"[\u10000-\uEFFFF]"
+    # )
+    ncnamestartchar = r"(?:[A-Z]|_|[a-z])"
+    # FIX UNICODE LATER
+    # ncnamechar = ncnamestartchar + (r"|-|\.|[0-9]|\u00B7|[\u0300-\u036F]|"
+    #                                 r"[\u203F-\u2040]")
+    ncnamechar = r"(?:" + ncnamestartchar + r"|-|\.|[0-9])"
+    ncname = f"(?:{ncnamestartchar}+{ncnamechar}*)"
+    pitarget_namestartchar = r"(?:[A-KN-WYZ]|_|:|[a-kn-wyz])"
+    pitarget_namechar = r"(?:" + pitarget_namestartchar + r"|-|\.|[0-9])"
+    pitarget = f"{pitarget_namestartchar}+{pitarget_namechar}*"
+    prefixedname = f"{ncname}:{ncname}"
+    unprefixedname = ncname
+    qname = f"(?:{prefixedname}|{unprefixedname})"
+
+    entityref = r'(?:&(?:lt|gt|amp|quot|apos|nbsp);)'
+    charref = r'(?:&#[0-9]+;|&#x[0-9a-fA-F]+;)'
+
+    stringdouble = r'(?:"(?:' + entityref + r'|' + charref + r'|""|[^&"])*")'
+    stringsingle = r"(?:'(?:" + entityref + r"|" + charref + r"|''|[^&'])*')"
+
+    # FIX UNICODE LATER
+    # elementcontentchar = (r'\t|\r|\n|[\u0020-\u0025]|[\u0028-\u003b]|'
+    #                       r'[\u003d-\u007a]|\u007c|[\u007e-\u007F]')
+    elementcontentchar = r'[A-Za-z]|\s|\d|[!"#$%()*+,\-./:;=?@\[\\\]^_\'`|~]'
+    # quotattrcontentchar = (r'\t|\r|\n|[\u0020-\u0021]|[\u0023-\u0025]|'
+    #                        r'[\u0027-\u003b]|[\u003d-\u007a]|\u007c|[\u007e-\u007F]')
+    quotattrcontentchar = r'[A-Za-z]|\s|\d|[!#$%()*+,\-./:;=?@\[\\\]^_\'`|~]'
+    # aposattrcontentchar = (r'\t|\r|\n|[\u0020-\u0025]|[\u0028-\u003b]|'
+    #                        r'[\u003d-\u007a]|\u007c|[\u007e-\u007F]')
+    aposattrcontentchar = r'[A-Za-z]|\s|\d|[!"#$%()*+,\-./:;=?@\[\\\]^_`|~]'
+
+    # CHAR elements - fix the above elementcontentchar, quotattrcontentchar,
+    #                 aposattrcontentchar
+    # x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
+
+    flags = re.DOTALL | re.MULTILINE
+
+    def punctuation_root_callback(lexer, match, ctx):
+        yield match.start(), Punctuation, match.group(1)
+        # transition to root always - don't pop off stack
+        ctx.stack = ['root']
+        ctx.pos = match.end()
+
+    def operator_root_callback(lexer, match, ctx):
+        yield match.start(), Operator, match.group(1)
+        # transition to root always - don't pop off stack
+        ctx.stack = ['root']
+        ctx.pos = match.end()
+
+    def popstate_tag_callback(lexer, match, ctx):
+        yield match.start(), Name.Tag, match.group(1)
+        if lexer.xquery_parse_state:
+            ctx.stack.append(lexer.xquery_parse_state.pop())
+        ctx.pos = match.end()
+
+    def popstate_xmlcomment_callback(lexer, match, ctx):
+        yield match.start(), String.Doc, match.group(1)
+        ctx.stack.append(lexer.xquery_parse_state.pop())
+        ctx.pos = match.end()
+
+    def popstate_kindtest_callback(lexer, match, ctx):
+        yield match.start(), Punctuation, match.group(1)
+        next_state = lexer.xquery_parse_state.pop()
+        if next_state == 'occurrenceindicator':
+            if re.match("[?*+]+", match.group(2)):
+                yield match.start(), Punctuation, match.group(2)
+                ctx.stack.append('operator')
+                ctx.pos = match.end()
+            else:
+                ctx.stack.append('operator')
+                ctx.pos = match.end(1)
+        else:
+            ctx.stack.append(next_state)
+            ctx.pos = match.end(1)
+
+    def popstate_callback(lexer, match, ctx):
+        yield match.start(), Punctuation, match.group(1)
+        # if we have run out of our state stack, pop whatever is on the pygments
+        # state stack
+        if len(lexer.xquery_parse_state) == 0:
+            ctx.stack.pop()
+            if not ctx.stack:
+                # make sure we have at least the root state on invalid inputs
+                ctx.stack = ['root']
+        elif len(ctx.stack) > 1:
+            ctx.stack.append(lexer.xquery_parse_state.pop())
+        else:
+            # i don't know if i'll need this, but in case, default back to root
+            ctx.stack = ['root']
+        ctx.pos = match.end()
+
+    def pushstate_element_content_starttag_callback(lexer, match, ctx):
+        yield match.start(), Name.Tag, match.group(1)
+        lexer.xquery_parse_state.append('element_content')
+        ctx.stack.append('start_tag')
+        ctx.pos = match.end()
+
+    def pushstate_cdata_section_callback(lexer, match, ctx):
+        yield match.start(), String.Doc, match.group(1)
+        ctx.stack.append('cdata_section')
+        lexer.xquery_parse_state.append(ctx.state.pop)
+        ctx.pos = match.end()
+
+    def pushstate_starttag_callback(lexer, match, ctx):
+        yield match.start(), Name.Tag, match.group(1)
+        lexer.xquery_parse_state.append(ctx.state.pop)
+        ctx.stack.append('start_tag')
+        ctx.pos = match.end()
+
+    def pushstate_operator_order_callback(lexer, match, ctx):
+        yield match.start(), Keyword, match.group(1)
+        yield match.start(), Whitespace, match.group(2)
+        yield match.start(), Punctuation, match.group(3)
+        ctx.stack = ['root']
+        lexer.xquery_parse_state.append('operator')
+        ctx.pos = match.end()
+
+    def pushstate_operator_map_callback(lexer, match, ctx):
+        yield match.start(), Keyword, match.group(1)
+        yield match.start(), Whitespace, match.group(2)
+        yield match.start(), Punctuation, match.group(3)
+        ctx.stack = ['root']
+        lexer.xquery_parse_state.append('operator')
+        ctx.pos = match.end()
+
+    def pushstate_operator_root_validate(lexer, match, ctx):
+        yield match.start(), Keyword, match.group(1)
+        yield match.start(), Whitespace, match.group(2)
+        yield match.start(), Punctuation, match.group(3)
+        ctx.stack = ['root']
+        lexer.xquery_parse_state.append('operator')
+        ctx.pos = match.end()
+
+    def pushstate_operator_root_validate_withmode(lexer, match, ctx):
+        yield match.start(), Keyword, match.group(1)
+        yield match.start(), Whitespace, match.group(2)
+        yield match.start(), Keyword, match.group(3)
+        ctx.stack = ['root']
+        lexer.xquery_parse_state.append('operator')
+        ctx.pos = match.end()
+
+    def pushstate_operator_processing_instruction_callback(lexer, match, ctx):
+        yield match.start(), String.Doc, match.group(1)
+        ctx.stack.append('processing_instruction')
+        lexer.xquery_parse_state.append('operator')
+        ctx.pos = match.end()
+
+    def pushstate_element_content_processing_instruction_callback(lexer, match, ctx):
+        yield match.start(), String.Doc, match.group(1)
+        ctx.stack.append('processing_instruction')
+        lexer.xquery_parse_state.append('element_content')
+        ctx.pos = match.end()
+
+    def pushstate_element_content_cdata_section_callback(lexer, match, ctx):
+        yield match.start(), String.Doc, match.group(1)
+        ctx.stack.append('cdata_section')
+        lexer.xquery_parse_state.append('element_content')
+        ctx.pos = match.end()
+
+    def pushstate_operator_cdata_section_callback(lexer, match, ctx):
+        yield match.start(), String.Doc, match.group(1)
+        ctx.stack.append('cdata_section')
+        lexer.xquery_parse_state.append('operator')
+        ctx.pos = match.end()
+
+    def pushstate_element_content_xmlcomment_callback(lexer, match, ctx):
+        yield match.start(), String.Doc, match.group(1)
+        ctx.stack.append('xml_comment')
+        lexer.xquery_parse_state.append('element_content')
+        ctx.pos = match.end()
+
+    def pushstate_operator_xmlcomment_callback(lexer, match, ctx):
+        yield match.start(), String.Doc, match.group(1)
+        ctx.stack.append('xml_comment')
+        lexer.xquery_parse_state.append('operator')
+        ctx.pos = match.end()
+
+    def pushstate_kindtest_callback(lexer, match, ctx):
+        yield match.start(), Keyword, match.group(1)
+        yield match.start(), Whitespace, match.group(2)
+        yield match.start(), Punctuation, match.group(3)
+        lexer.xquery_parse_state.append('kindtest')
+        ctx.stack.append('kindtest')
+        ctx.pos = match.end()
+
+    def pushstate_operator_kindtestforpi_callback(lexer, match, ctx):
+        yield match.start(), Keyword, match.group(1)
+        yield match.start(), Whitespace, match.group(2)
+        yield match.start(), Punctuation, match.group(3)
+        lexer.xquery_parse_state.append('operator')
+        ctx.stack.append('kindtestforpi')
+        ctx.pos = match.end()
+
+    def pushstate_operator_kindtest_callback(lexer, match, ctx):
+        yield match.start(), Keyword, match.group(1)
+        yield match.start(), Whitespace, match.group(2)
+        yield match.start(), Punctuation, match.group(3)
+        lexer.xquery_parse_state.append('operator')
+        ctx.stack.append('kindtest')
+        ctx.pos = match.end()
+
+    def pushstate_occurrenceindicator_kindtest_callback(lexer, match, ctx):
+        yield match.start(), Name.Tag, match.group(1)
+        yield match.start(), Whitespace, match.group(2)
+        yield match.start(), Punctuation, match.group(3)
+        lexer.xquery_parse_state.append('occurrenceindicator')
+        ctx.stack.append('kindtest')
+        ctx.pos = match.end()
+
+    def pushstate_operator_starttag_callback(lexer, match, ctx):
+        yield match.start(), Name.Tag, match.group(1)
+        lexer.xquery_parse_state.append('operator')
+        ctx.stack.append('start_tag')
+        ctx.pos = match.end()
+
+    def pushstate_operator_root_callback(lexer, match, ctx):
+        yield match.start(), Punctuation, match.group(1)
+        lexer.xquery_parse_state.append('operator')
+        ctx.stack = ['root']
+        ctx.pos = match.end()
+
+    def pushstate_operator_root_construct_callback(lexer, match, ctx):
+        yield match.start(), Keyword, match.group(1)
+        yield match.start(), Whitespace, match.group(2)
+        yield match.start(), Punctuation, match.group(3)
+        lexer.xquery_parse_state.append('operator')
+        ctx.stack = ['root']
+        ctx.pos = match.end()
+
+    def pushstate_root_callback(lexer, match, ctx):
+        yield match.start(), Punctuation, match.group(1)
+        cur_state = ctx.stack.pop()
+        lexer.xquery_parse_state.append(cur_state)
+        ctx.stack = ['root']
+        ctx.pos = match.end()
+
+    def pushstate_operator_attribute_callback(lexer, match, ctx):
+        yield match.start(), Name.Attribute, match.group(1)
+        ctx.stack.append('operator')
+        ctx.pos = match.end()
+
+    tokens = {
+        'comment': [
+            # xquery comments
+            (r'[^:()]+', Comment),
+            (r'\(:', Comment, '#push'),
+            (r':\)', Comment, '#pop'),
+            (r'[:()]', Comment),
+        ],
+        'whitespace': [
+            (r'\s+', Whitespace),
+        ],
+        'operator': [
+            include('whitespace'),
+            (r'(\})', popstate_callback),
+            (r'\(:', Comment, 'comment'),
+
+            (r'(\{)', pushstate_root_callback),
+            (r'then|else|external|at|div|except', Keyword, 'root'),
+            (r'order by', Keyword, 'root'),
+            (r'group by', Keyword, 'root'),
+            (r'is|mod|order\s+by|stable\s+order\s+by', Keyword, 'root'),
+            (r'and|or', Operator.Word, 'root'),
+            (r'(eq|ge|gt|le|lt|ne|idiv|intersect|in)(?=\b)',
+             Operator.Word, 'root'),
+            (r'return|satisfies|to|union|where|count|preserve\s+strip',
+             Keyword, 'root'),
+            (r'(>=|>>|>|<=|<<|<|-|\*|!=|\+|\|\||\||:=|=|!)',
+             operator_root_callback),
+            (r'(::|:|;|\[|//|/|,)',
+             punctuation_root_callback),
+            (r'(castable|cast)(\s+)(as)\b',
+             bygroups(Keyword, Whitespace, Keyword), 'singletype'),
+            (r'(instance)(\s+)(of)\b',
+             bygroups(Keyword, Whitespace, Keyword), 'itemtype'),
+            (r'(treat)(\s+)(as)\b',
+             bygroups(Keyword, Whitespace, Keyword), 'itemtype'),
+            (r'(case)(\s+)(' + stringdouble + ')',
+             bygroups(Keyword, Whitespace, String.Double), 'itemtype'),
+            (r'(case)(\s+)(' + stringsingle + ')',
+             bygroups(Keyword, Whitespace, String.Single), 'itemtype'),
+            (r'(case|as)\b', Keyword, 'itemtype'),
+            (r'(\))(\s*)(as)',
+             bygroups(Punctuation, Whitespace, Keyword), 'itemtype'),
+            (r'\$', Name.Variable, 'varname'),
+            (r'(for|let|previous|next)(\s+)(\$)',
+             bygroups(Keyword, Whitespace, Name.Variable), 'varname'),
+            (r'(for)(\s+)(tumbling|sliding)(\s+)(window)(\s+)(\$)',
+             bygroups(Keyword, Whitespace, Keyword, Whitespace, Keyword,
+                      Whitespace, Name.Variable),
+             'varname'),
+            # (r'\)|\?|\]', Punctuation, '#push'),
+            (r'\)|\?|\]', Punctuation),
+            (r'(empty)(\s+)(greatest|least)',
+             bygroups(Keyword, Whitespace, Keyword)),
+            (r'ascending|descending|default', Keyword, '#push'),
+            (r'(allowing)(\s+)(empty)',
+             bygroups(Keyword, Whitespace, Keyword)),
+            (r'external', Keyword),
+            (r'(start|when|end)', Keyword, 'root'),
+            (r'(only)(\s+)(end)', bygroups(Keyword, Whitespace, Keyword),
+             'root'),
+            (r'collation', Keyword, 'uritooperator'),
+
+            # eXist specific XQUF
+            (r'(into|following|preceding|with)', Keyword, 'root'),
+
+            # support for current context on rhs of Simple Map Operator
+            (r'\.', Operator),
+
+            # finally catch all string literals and stay in operator state
+            (stringdouble, String.Double),
+            (stringsingle, String.Single),
+
+            (r'(catch)(\s*)', bygroups(Keyword, Whitespace), 'root'),
+        ],
+        'uritooperator': [
+            (stringdouble, String.Double, '#pop'),
+            (stringsingle, String.Single, '#pop'),
+        ],
+        'namespacedecl': [
+            include('whitespace'),
+            (r'\(:', Comment, 'comment'),
+            (r'(at)(\s+)('+stringdouble+')',
+             bygroups(Keyword, Whitespace, String.Double)),
+            (r"(at)(\s+)("+stringsingle+')',
+             bygroups(Keyword, Whitespace, String.Single)),
+            (stringdouble, String.Double),
+            (stringsingle, String.Single),
+            (r',', Punctuation),
+            (r'=', Operator),
+            (r';', Punctuation, 'root'),
+            (ncname, Name.Namespace),
+        ],
+        'namespacekeyword': [
+            include('whitespace'),
+            (r'\(:', Comment, 'comment'),
+            (stringdouble, String.Double, 'namespacedecl'),
+            (stringsingle, String.Single, 'namespacedecl'),
+            (r'inherit|no-inherit', Keyword, 'root'),
+            (r'namespace', Keyword, 'namespacedecl'),
+            (r'(default)(\s+)(element)', bygroups(Keyword, Text, Keyword)),
+            (r'preserve|no-preserve', Keyword),
+            (r',', Punctuation),
+        ],
+        'annotationname': [
+            (r'\(:', Comment, 'comment'),
+            (qname, Name.Decorator),
+            (r'(\()(' + stringdouble + ')', bygroups(Punctuation, String.Double)),
+            (r'(\()(' + stringsingle + ')', bygroups(Punctuation, String.Single)),
+            (r'(\,)(\s+)(' + stringdouble + ')',
+             bygroups(Punctuation, Text, String.Double)),
+            (r'(\,)(\s+)(' + stringsingle + ')',
+             bygroups(Punctuation, Text, String.Single)),
+            (r'\)', Punctuation),
+            (r'(\s+)(\%)', bygroups(Text, Name.Decorator), 'annotationname'),
+            (r'(\s+)(variable)(\s+)(\$)',
+             bygroups(Text, Keyword.Declaration, Text, Name.Variable), 'varname'),
+            (r'(\s+)(function)(\s+)',
+             bygroups(Text, Keyword.Declaration, Text), 'root')
+        ],
+        'varname': [
+            (r'\(:', Comment, 'comment'),
+            (r'(' + qname + r')(\()?', bygroups(Name, Punctuation), 'operator'),
+        ],
+        'singletype': [
+            include('whitespace'),
+            (r'\(:', Comment, 'comment'),
+            (ncname + r'(:\*)', Name.Variable, 'operator'),
+            (qname, Name.Variable, 'operator'),
+        ],
+        'itemtype': [
+            include('whitespace'),
+            (r'\(:', Comment, 'comment'),
+            (r'\$', Name.Variable, 'varname'),
+            (r'(void)(\s*)(\()(\s*)(\))',
+             bygroups(Keyword, Text, Punctuation, Text, Punctuation), 'operator'),
+            (r'(element|attribute|schema-element|schema-attribute|comment|text|'
+             r'node|binary|document-node|empty-sequence)(\s*)(\()',
+             pushstate_occurrenceindicator_kindtest_callback),
+            # Marklogic specific type?
+            (r'(processing-instruction)(\s*)(\()',
+             bygroups(Keyword, Text, Punctuation),
+             ('occurrenceindicator', 'kindtestforpi')),
+            (r'(item)(\s*)(\()(\s*)(\))(?=[*+?])',
+             bygroups(Keyword, Text, Punctuation, Text, Punctuation),
+             'occurrenceindicator'),
+            (r'(\(\#)(\s*)', bygroups(Punctuation, Text), 'pragma'),
+            (r';', Punctuation, '#pop'),
+            (r'then|else', Keyword, '#pop'),
+            (r'(at)(\s+)(' + stringdouble + ')',
+             bygroups(Keyword, Text, String.Double), 'namespacedecl'),
+            (r'(at)(\s+)(' + stringsingle + ')',
+             bygroups(Keyword, Text, String.Single), 'namespacedecl'),
+            (r'except|intersect|in|is|return|satisfies|to|union|where|count',
+             Keyword, 'root'),
+            (r'and|div|eq|ge|gt|le|lt|ne|idiv|mod|or', Operator.Word, 'root'),
+            (r':=|=|,|>=|>>|>|\[|\(|<=|<<|<|-|!=|\|\||\|', Operator, 'root'),
+            (r'external|at', Keyword, 'root'),
+            (r'(stable)(\s+)(order)(\s+)(by)',
+             bygroups(Keyword, Text, Keyword, Text, Keyword), 'root'),
+            (r'(castable|cast)(\s+)(as)',
+             bygroups(Keyword, Text, Keyword), 'singletype'),
+            (r'(treat)(\s+)(as)', bygroups(Keyword, Text, Keyword)),
+            (r'(instance)(\s+)(of)', bygroups(Keyword, Text, Keyword)),
+            (r'(case)(\s+)(' + stringdouble + ')',
+             bygroups(Keyword, Text, String.Double), 'itemtype'),
+            (r'(case)(\s+)(' + stringsingle + ')',
+             bygroups(Keyword, Text, String.Single), 'itemtype'),
+            (r'case|as', Keyword, 'itemtype'),
+            (r'(\))(\s*)(as)', bygroups(Operator, Text, Keyword), 'itemtype'),
+            (ncname + r':\*', Keyword.Type, 'operator'),
+            (r'(function|map|array)(\()', bygroups(Keyword.Type, Punctuation)),
+            (qname, Keyword.Type, 'occurrenceindicator'),
+        ],
+        'kindtest': [
+            (r'\(:', Comment, 'comment'),
+            (r'\{', Punctuation, 'root'),
+            (r'(\))([*+?]?)', popstate_kindtest_callback),
+            (r'\*', Name, 'closekindtest'),
+            (qname, Name, 'closekindtest'),
+            (r'(element|schema-element)(\s*)(\()', pushstate_kindtest_callback),
+        ],
+        'kindtestforpi': [
+            (r'\(:', Comment, 'comment'),
+            (r'\)', Punctuation, '#pop'),
+            (ncname, Name.Variable),
+            (stringdouble, String.Double),
+            (stringsingle, String.Single),
+        ],
+        'closekindtest': [
+            (r'\(:', Comment, 'comment'),
+            (r'(\))', popstate_callback),
+            (r',', Punctuation),
+            (r'(\{)', pushstate_operator_root_callback),
+            (r'\?', Punctuation),
+        ],
+        'xml_comment': [
+            (r'(-->)', popstate_xmlcomment_callback),
+            (r'[^-]{1,2}', Literal),
+            (r'\t|\r|\n|[\u0020-\uD7FF]|[\uE000-\uFFFD]|[\U00010000-\U0010FFFF]',
+             Literal),
+        ],
+        'processing_instruction': [
+            (r'\s+', Text, 'processing_instruction_content'),
+            (r'\?>', String.Doc, '#pop'),
+            (pitarget, Name),
+        ],
+        'processing_instruction_content': [
+            (r'\?>', String.Doc, '#pop'),
+            (r'\t|\r|\n|[\u0020-\uD7FF]|[\uE000-\uFFFD]|[\U00010000-\U0010FFFF]',
+             Literal),
+        ],
+        'cdata_section': [
+            (r']]>', String.Doc, '#pop'),
+            (r'\t|\r|\n|[\u0020-\uD7FF]|[\uE000-\uFFFD]|[\U00010000-\U0010FFFF]',
+             Literal),
+        ],
+        'start_tag': [
+            include('whitespace'),
+            (r'(/>)', popstate_tag_callback),
+            (r'>', Name.Tag, 'element_content'),
+            (r'"', Punctuation, 'quot_attribute_content'),
+            (r"'", Punctuation, 'apos_attribute_content'),
+            (r'=', Operator),
+            (qname, Name.Tag),
+        ],
+        'quot_attribute_content': [
+            (r'"', Punctuation, 'start_tag'),
+            (r'(\{)', pushstate_root_callback),
+            (r'""', Name.Attribute),
+            (quotattrcontentchar, Name.Attribute),
+            (entityref, Name.Attribute),
+            (charref, Name.Attribute),
+            (r'\{\{|\}\}', Name.Attribute),
+        ],
+        'apos_attribute_content': [
+            (r"'", Punctuation, 'start_tag'),
+            (r'\{', Punctuation, 'root'),
+            (r"''", Name.Attribute),
+            (aposattrcontentchar, Name.Attribute),
+            (entityref, Name.Attribute),
+            (charref, Name.Attribute),
+            (r'\{\{|\}\}', Name.Attribute),
+        ],
+        'element_content': [
+            (r'</', Name.Tag, 'end_tag'),
+            (r'(\{)', pushstate_root_callback),
+            (r'(<!--)', pushstate_element_content_xmlcomment_callback),
+            (r'(<\?)', pushstate_element_content_processing_instruction_callback),
+            (r'(<!\[CDATA\[)', pushstate_element_content_cdata_section_callback),
+            (r'(<)', pushstate_element_content_starttag_callback),
+            (elementcontentchar, Literal),
+            (entityref, Literal),
+            (charref, Literal),
+            (r'\{\{|\}\}', Literal),
+        ],
+        'end_tag': [
+            include('whitespace'),
+            (r'(>)', popstate_tag_callback),
+            (qname, Name.Tag),
+        ],
+        'xmlspace_decl': [
+            include('whitespace'),
+            (r'\(:', Comment, 'comment'),
+            (r'preserve|strip', Keyword, '#pop'),
+        ],
+        'declareordering': [
+            (r'\(:', Comment, 'comment'),
+            include('whitespace'),
+            (r'ordered|unordered', Keyword, '#pop'),
+        ],
+        'xqueryversion': [
+            include('whitespace'),
+            (r'\(:', Comment, 'comment'),
+            (stringdouble, String.Double),
+            (stringsingle, String.Single),
+            (r'encoding', Keyword),
+            (r';', Punctuation, '#pop'),
+        ],
+        'pragma': [
+            (qname, Name.Variable, 'pragmacontents'),
+        ],
+        'pragmacontents': [
+            (r'#\)', Punctuation, 'operator'),
+            (r'\t|\r|\n|[\u0020-\uD7FF]|[\uE000-\uFFFD]|[\U00010000-\U0010FFFF]',
+             Literal),
+            (r'(\s+)', Whitespace),
+        ],
+        'occurrenceindicator': [
+            include('whitespace'),
+            (r'\(:', Comment, 'comment'),
+            (r'\*|\?|\+', Operator, 'operator'),
+            (r':=', Operator, 'root'),
+            default('operator'),
+        ],
+        'option': [
+            include('whitespace'),
+            (qname, Name.Variable, '#pop'),
+        ],
+        'qname_braren': [
+            include('whitespace'),
+            (r'(\{)', pushstate_operator_root_callback),
+            (r'(\()', Punctuation, 'root'),
+        ],
+        'element_qname': [
+            (qname, Name.Variable, 'root'),
+        ],
+        'attribute_qname': [
+            (qname, Name.Variable, 'root'),
+        ],
+        'root': [
+            include('whitespace'),
+            (r'\(:', Comment, 'comment'),
+
+            # handle operator state
+            # order on numbers matters - handle most complex first
+            (r'\d+(\.\d*)?[eE][+-]?\d+', Number.Float, 'operator'),
+            (r'(\.\d+)[eE][+-]?\d+', Number.Float, 'operator'),
+            (r'(\.\d+|\d+\.\d*)', Number.Float, 'operator'),
+            (r'(\d+)', Number.Integer, 'operator'),
+            (r'(\.\.|\.|\))', Punctuation, 'operator'),
+            (r'(declare)(\s+)(construction)',
+             bygroups(Keyword.Declaration, Text, Keyword.Declaration), 'operator'),
+            (r'(declare)(\s+)(default)(\s+)(order)',
+             bygroups(Keyword.Declaration, Text, Keyword.Declaration, Text, Keyword.Declaration), 'operator'),
+            (r'(declare)(\s+)(context)(\s+)(item)',
+             bygroups(Keyword.Declaration, Text, Keyword.Declaration, Text, Keyword.Declaration), 'operator'),
+            (ncname + r':\*', Name, 'operator'),
+            (r'\*:'+ncname, Name.Tag, 'operator'),
+            (r'\*', Name.Tag, 'operator'),
+            (stringdouble, String.Double, 'operator'),
+            (stringsingle, String.Single, 'operator'),
+
+            (r'(\}|\])', popstate_callback),
+
+            # NAMESPACE DECL
+            (r'(declare)(\s+)(default)(\s+)(collation)',
+             bygroups(Keyword.Declaration, Whitespace, Keyword.Declaration,
+                      Whitespace, Keyword.Declaration)),
+            (r'(module|declare)(\s+)(namespace)',
+             bygroups(Keyword.Declaration, Whitespace, Keyword.Declaration),
+             'namespacedecl'),
+            (r'(declare)(\s+)(base-uri)',
+             bygroups(Keyword.Declaration, Whitespace, Keyword.Declaration),
+             'namespacedecl'),
+
+            # NAMESPACE KEYWORD
+            (r'(declare)(\s+)(default)(\s+)(element|function)',
+             bygroups(Keyword.Declaration, Whitespace, Keyword.Declaration,
+                      Whitespace, Keyword.Declaration),
+             'namespacekeyword'),
+            (r'(import)(\s+)(schema|module)',
+             bygroups(Keyword.Pseudo, Whitespace, Keyword.Pseudo),
+             'namespacekeyword'),
+            (r'(declare)(\s+)(copy-namespaces)',
+             bygroups(Keyword.Declaration, Whitespace, Keyword.Declaration),
+             'namespacekeyword'),
+
+            # VARNAMEs
+            (r'(for|let|some|every)(\s+)(\$)',
+             bygroups(Keyword, Whitespace, Name.Variable), 'varname'),
+            (r'(for)(\s+)(tumbling|sliding)(\s+)(window)(\s+)(\$)',
+             bygroups(Keyword, Whitespace, Keyword, Whitespace, Keyword,
+                      Whitespace, Name.Variable),
+             'varname'),
+            (r'\$', Name.Variable, 'varname'),
+            (r'(declare)(\s+)(variable)(\s+)(\$)',
+             bygroups(Keyword.Declaration, Whitespace, Keyword.Declaration,
+                      Whitespace, Name.Variable),
+             'varname'),
+
+            # ANNOTATED GLOBAL VARIABLES AND FUNCTIONS
+            (r'(declare)(\s+)(\%)', bygroups(Keyword.Declaration, Whitespace,
+                                             Name.Decorator),
+             'annotationname'),
+
+            # ITEMTYPE
+            (r'(\))(\s+)(as)', bygroups(Operator, Whitespace, Keyword),
+             'itemtype'),
+
+            (r'(element|attribute|schema-element|schema-attribute|comment|'
+             r'text|node|document-node|empty-sequence)(\s+)(\()',
+             pushstate_operator_kindtest_callback),
+
+            (r'(processing-instruction)(\s+)(\()',
+             pushstate_operator_kindtestforpi_callback),
+
+            (r'(<!--)', pushstate_operator_xmlcomment_callback),
+
+            (r'(<\?)', pushstate_operator_processing_instruction_callback),
+
+            (r'(<!\[CDATA\[)', pushstate_operator_cdata_section_callback),
+
+            # (r'</', Name.Tag, 'end_tag'),
+            (r'(<)', pushstate_operator_starttag_callback),
+
+            (r'(declare)(\s+)(boundary-space)',
+             bygroups(Keyword.Declaration, Text, Keyword.Declaration), 'xmlspace_decl'),
+
+            (r'(validate)(\s+)(lax|strict)',
+             pushstate_operator_root_validate_withmode),
+            (r'(validate)(\s*)(\{)', pushstate_operator_root_validate),
+            (r'(typeswitch)(\s*)(\()', bygroups(Keyword, Whitespace,
+                                                Punctuation)),
+            (r'(switch)(\s*)(\()', bygroups(Keyword, Whitespace, Punctuation)),
+            (r'(element|attribute|namespace)(\s*)(\{)',
+             pushstate_operator_root_construct_callback),
+
+            (r'(document|text|processing-instruction|comment)(\s*)(\{)',
+             pushstate_operator_root_construct_callback),
+            # ATTRIBUTE
+            (r'(attribute)(\s+)(?=' + qname + r')',
+             bygroups(Keyword, Whitespace), 'attribute_qname'),
+            # ELEMENT
+            (r'(element)(\s+)(?=' + qname + r')',
+             bygroups(Keyword, Whitespace), 'element_qname'),
+            # PROCESSING_INSTRUCTION
+            (r'(processing-instruction|namespace)(\s+)(' + ncname + r')(\s*)(\{)',
+             bygroups(Keyword, Whitespace, Name.Variable, Whitespace,
+                      Punctuation),
+             'operator'),
+
+            (r'(declare|define)(\s+)(function)',
+             bygroups(Keyword.Declaration, Whitespace, Keyword.Declaration)),
+
+            (r'(\{|\[)', pushstate_operator_root_callback),
+
+            (r'(unordered|ordered)(\s*)(\{)',
+             pushstate_operator_order_callback),
+
+            (r'(map|array)(\s*)(\{)',
+             pushstate_operator_map_callback),
+
+            (r'(declare)(\s+)(ordering)',
+             bygroups(Keyword.Declaration, Whitespace, Keyword.Declaration),
+             'declareordering'),
+
+            (r'(xquery)(\s+)(version)',
+             bygroups(Keyword.Pseudo, Whitespace, Keyword.Pseudo),
+             'xqueryversion'),
+
+            (r'(\(#)(\s*)', bygroups(Punctuation, Whitespace), 'pragma'),
+
+            # sometimes return can occur in root state
+            (r'return', Keyword),
+
+            (r'(declare)(\s+)(option)', bygroups(Keyword.Declaration,
+                                                 Whitespace,
+                                                 Keyword.Declaration),
+             'option'),
+
+            # URI LITERALS - single and double quoted
+            (r'(at)(\s+)('+stringdouble+')', String.Double, 'namespacedecl'),
+            (r'(at)(\s+)('+stringsingle+')', String.Single, 'namespacedecl'),
+
+            (r'(ancestor-or-self|ancestor|attribute|child|descendant-or-self)(::)',
+             bygroups(Keyword, Punctuation)),
+            (r'(descendant|following-sibling|following|parent|preceding-sibling'
+             r'|preceding|self)(::)', bygroups(Keyword, Punctuation)),
+
+            (r'(if)(\s*)(\()', bygroups(Keyword, Whitespace, Punctuation)),
+
+            (r'then|else', Keyword),
+
+            # eXist specific XQUF
+            (r'(update)(\s*)(insert|delete|replace|value|rename)',
+             bygroups(Keyword, Whitespace, Keyword)),
+            (r'(into|following|preceding|with)', Keyword),
+
+            # Marklogic specific
+            (r'(try)(\s*)', bygroups(Keyword, Whitespace), 'root'),
+            (r'(catch)(\s*)(\()(\$)',
+             bygroups(Keyword, Whitespace, Punctuation, Name.Variable),
+             'varname'),
+
+
+            (r'(@'+qname+')', Name.Attribute, 'operator'),
+            (r'(@'+ncname+')', Name.Attribute, 'operator'),
+            (r'@\*:'+ncname, Name.Attribute, 'operator'),
+            (r'@\*', Name.Attribute, 'operator'),
+            (r'(@)', Name.Attribute, 'operator'),
+
+            (r'//|/|\+|-|;|,|\(|\)', Punctuation),
+
+            # STANDALONE QNAMES
+            (qname + r'(?=\s*\{)', Name.Tag, 'qname_braren'),
+            (qname + r'(?=\s*\([^:])', Name.Function, 'qname_braren'),
+            (r'(' + qname + ')(#)([0-9]+)', bygroups(Name.Function, Keyword.Type, Number.Integer)),
+            (qname, Name.Tag, 'operator'),
+        ]
+    }
+
+
+class QmlLexer(RegexLexer):
+    """
+    For QML files.
+    """
+
+    # QML is based on javascript, so much of this is taken from the
+    # JavascriptLexer above.
+
+    name = 'QML'
+    url = 'https://doc.qt.io/qt-6/qmlapplications.html'
+    aliases = ['qml', 'qbs']
+    filenames = ['*.qml', '*.qbs']
+    mimetypes = ['application/x-qml', 'application/x-qt.qbs+qml']
+    version_added = '1.6'
+
+    # pasted from JavascriptLexer, with some additions
+    flags = re.DOTALL | re.MULTILINE
+
+    tokens = {
+        'commentsandwhitespace': [
+            (r'\s+', Text),
+            (r'<!--', Comment),
+            (r'//.*?\n', Comment.Single),
+            (r'/\*.*?\*/', Comment.Multiline)
+        ],
+        'slashstartsregex': [
+            include('commentsandwhitespace'),
+            (r'/(\\.|[^[/\\\n]|\[(\\.|[^\]\\\n])*])+/'
+             r'([gim]+\b|\B)', String.Regex, '#pop'),
+            (r'(?=/)', Text, ('#pop', 'badregex')),
+            default('#pop')
+        ],
+        'badregex': [
+            (r'\n', Text, '#pop')
+        ],
+        'root': [
+            (r'^(?=\s|/|<!--)', Text, 'slashstartsregex'),
+            include('commentsandwhitespace'),
+            (r'\+\+|--|~|&&|\?|:|\|\||\\(?=\n)|'
+             r'(<<|>>>?|==?|!=?|[-<>+*%&|^/])=?', Operator, 'slashstartsregex'),
+            (r'[{(\[;,]', Punctuation, 'slashstartsregex'),
+            (r'[})\].]', Punctuation),
+
+            # QML insertions
+            (r'\bid\s*:\s*[A-Za-z][\w.]*', Keyword.Declaration,
+             'slashstartsregex'),
+            (r'\b[A-Za-z][\w.]*\s*:', Keyword, 'slashstartsregex'),
+
+            # the rest from JavascriptLexer
+            (r'(for|in|while|do|break|return|continue|switch|case|default|if|else|'
+             r'throw|try|catch|finally|new|delete|typeof|instanceof|void|'
+             r'this)\b', Keyword, 'slashstartsregex'),
+            (r'(var|let|with|function)\b', Keyword.Declaration, 'slashstartsregex'),
+            (r'(abstract|boolean|byte|char|class|const|debugger|double|enum|export|'
+             r'extends|final|float|goto|implements|import|int|interface|long|native|'
+             r'package|private|protected|public|short|static|super|synchronized|throws|'
+             r'transient|volatile)\b', Keyword.Reserved),
+            (r'(true|false|null|NaN|Infinity|undefined)\b', Keyword.Constant),
+            (r'(Array|Boolean|Date|Error|Function|Math|netscape|'
+             r'Number|Object|Packages|RegExp|String|sun|decodeURI|'
+             r'decodeURIComponent|encodeURI|encodeURIComponent|'
+             r'Error|eval|isFinite|isNaN|parseFloat|parseInt|document|this|'
+             r'window)\b', Name.Builtin),
+            (r'[$a-zA-Z_]\w*', Name.Other),
+            (r'[0-9][0-9]*\.[0-9]+([eE][0-9]+)?[fd]?', Number.Float),
+            (r'0x[0-9a-fA-F]+', Number.Hex),
+            (r'[0-9]+', Number.Integer),
+            (r'"(\\\\|\\[^\\]|[^"\\])*"', String.Double),
+            (r"'(\\\\|\\[^\\]|[^'\\])*'", String.Single),
+        ]
+    }
+
+
+class CirruLexer(RegexLexer):
+    r"""
+    * using ``()`` for expressions, but restricted in a same line
+    * using ``""`` for strings, with ``\`` for escaping chars
+    * using ``$`` as folding operator
+    * using ``,`` as unfolding operator
+    * using indentations for nested blocks
+    """
+
+    name = 'Cirru'
+    url = 'http://cirru.org/'
+    aliases = ['cirru']
+    filenames = ['*.cirru']
+    mimetypes = ['text/x-cirru']
+    version_added = '2.0'
+    flags = re.MULTILINE
+
+    tokens = {
+        'string': [
+            (r'[^"\\\n]+', String),
+            (r'\\', String.Escape, 'escape'),
+            (r'"', String, '#pop'),
+        ],
+        'escape': [
+            (r'.', String.Escape, '#pop'),
+        ],
+        'function': [
+            (r'\,', Operator, '#pop'),
+            (r'[^\s"()]+', Name.Function, '#pop'),
+            (r'\)', Operator, '#pop'),
+            (r'(?=\n)', Text, '#pop'),
+            (r'\(', Operator, '#push'),
+            (r'"', String, ('#pop', 'string')),
+            (r'[ ]+', Text.Whitespace),
+        ],
+        'line': [
+            (r'(?<!\w)\$(?!\w)', Operator, 'function'),
+            (r'\(', Operator, 'function'),
+            (r'\)', Operator),
+            (r'\n', Text, '#pop'),
+            (r'"', String, 'string'),
+            (r'[ ]+', Text.Whitespace),
+            (r'[+-]?[\d.]+\b', Number),
+            (r'[^\s"()]+', Name.Variable)
+        ],
+        'root': [
+            (r'^\n+', Text.Whitespace),
+            default(('line', 'function')),
+        ]
+    }
+
+
+class SlimLexer(ExtendedRegexLexer):
+    """
+    For Slim markup.
+    """
+
+    name = 'Slim'
+    aliases = ['slim']
+    filenames = ['*.slim']
+    mimetypes = ['text/x-slim']
+    url = 'https://slim-template.github.io'
+    version_added = '2.0'
+
+    flags = re.IGNORECASE
+    _dot = r'(?: \|\n(?=.* \|)|.)'
+    tokens = {
+        'root': [
+            (r'[ \t]*\n', Text),
+            (r'[ \t]*', _indentation),
+        ],
+
+        'css': [
+            (r'\.[\w:-]+', Name.Class, 'tag'),
+            (r'\#[\w:-]+', Name.Function, 'tag'),
+        ],
+
+        'eval-or-plain': [
+            (r'([ \t]*==?)(.*\n)',
+             bygroups(Punctuation, using(RubyLexer)),
+             'root'),
+            (r'[ \t]+[\w:-]+(?==)', Name.Attribute, 'html-attributes'),
+            default('plain'),
+        ],
+
+        'content': [
+            include('css'),
+            (r'[\w:-]+:[ \t]*\n', Text, 'plain'),
+            (r'(-)(.*\n)',
+             bygroups(Punctuation, using(RubyLexer)),
+             '#pop'),
+            (r'\|' + _dot + r'*\n', _starts_block(Text, 'plain'), '#pop'),
+            (r'/' + _dot + r'*\n', _starts_block(Comment.Preproc, 'slim-comment-block'), '#pop'),
+            (r'[\w:-]+', Name.Tag, 'tag'),
+            include('eval-or-plain'),
+        ],
+
+        'tag': [
+            include('css'),
+            (r'[<>]{1,2}(?=[ \t=])', Punctuation),
+            (r'[ \t]+\n', Punctuation, '#pop:2'),
+            include('eval-or-plain'),
+        ],
+
+        'plain': [
+            (r'([^#\n]|#[^{\n]|(\\\\)*\\#\{)+', Text),
+            (r'(#\{)(.*?)(\})',
+             bygroups(String.Interpol, using(RubyLexer), String.Interpol)),
+            (r'\n', Text, 'root'),
+        ],
+
+        'html-attributes': [
+            (r'=', Punctuation),
+            (r'"[^"]+"', using(RubyLexer), 'tag'),
+            (r'\'[^\']+\'', using(RubyLexer), 'tag'),
+            (r'\w+', Text, 'tag'),
+        ],
+
+        'slim-comment-block': [
+            (_dot + '+', Comment.Preproc),
+            (r'\n', Text, 'root'),
+        ],
+    }

LTA_openwebtext_dualt/mini_owt_logdirichlet/.venv_qwen35_uv/lib/python3.12/site-packages/pygments/lexers/x10.py

@@ -0,0 +1,66 @@
+"""
+    pygments.lexers.x10
+    ~~~~~~~~~~~~~~~~~~~
+
+    Lexers for the X10 programming language.
+
+    :copyright: Copyright 2006-present by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.lexer import RegexLexer
+from pygments.token import Text, Comment, Keyword, String
+
+__all__ = ['X10Lexer']
+
+
+class X10Lexer(RegexLexer):
+    """
+    For the X10 language.
+    """
+
+    name = 'X10'
+    url = 'http://x10-lang.org/'
+    aliases = ['x10', 'xten']
+    filenames = ['*.x10']
+    mimetypes = ['text/x-x10']
+    version_added = '2.2'
+
+    keywords = (
+        'as', 'assert', 'async', 'at', 'athome', 'ateach', 'atomic',
+        'break', 'case', 'catch', 'class', 'clocked', 'continue',
+        'def', 'default', 'do', 'else', 'final', 'finally', 'finish',
+        'for', 'goto', 'haszero', 'here', 'if', 'import', 'in',
+        'instanceof', 'interface', 'isref', 'new', 'offer',
+        'operator', 'package', 'return', 'struct', 'switch', 'throw',
+        'try', 'type', 'val', 'var', 'when', 'while'
+    )
+
+    types = (
+        'void'
+    )
+
+    values = (
+        'false', 'null', 'self', 'super', 'this', 'true'
+    )
+
+    modifiers = (
+        'abstract', 'extends', 'implements', 'native', 'offers',
+        'private', 'property', 'protected', 'public', 'static',
+        'throws', 'transient'
+    )
+
+    tokens = {
+        'root': [
+            (r'[^\S\n]+', Text),
+            (r'//.*?\n', Comment.Single),
+            (r'/\*(.|\n)*?\*/', Comment.Multiline),
+            (r'\b({})\b'.format('|'.join(keywords)), Keyword),
+            (r'\b({})\b'.format('|'.join(types)), Keyword.Type),
+            (r'\b({})\b'.format('|'.join(values)), Keyword.Constant),
+            (r'\b({})\b'.format('|'.join(modifiers)), Keyword.Declaration),
+            (r'"(\\\\|\\[^\\]|[^"\\])*"', String),
+            (r"'\\.'|'[^\\]'|'\\u[0-9a-fA-F]{4}'", String.Char),
+            (r'.', Text)
+        ],
+    }