[feat|WHT] add LOAD_FILE and AI_SPLIT_DOCUMENT

[wht0not]

Description

Implement the two Document AI functions required by task 2:

• Add LOAD_FILE(location_name, file_name) to read files from a local file:// LOCATION and return BLOB data.
• Add AI_SPLIT_DOCUMENT(content[, parameters]) to split text or Markdown by word or sentence with configurable max and overlap.
• Register the new expressions and integrate parser, resolver, runtime evaluation, and build configuration.

Testing

• Successfully built seekdb.exe on Windows.
• Verified both functions against the existing ai_funcs mysqltest expectations.
• PyMySQL acceptance tests pass for file loading, sentence splitting, word overlap, Markdown headings, and max=2.

[LINxiansheng]

Document AI & IK Custom Dictionary Score

Document AI Functions Score
===========================
score: 100.00 / 100
load_file: 50 / 50
ai_split_document: 50 / 50

IK Custom Dictionary Score
==========================
score: 100.00 / 100
ik_custom_dict: 100 / 100

FTS Large Benchmark Score

FTS Large Benchmark Score
=========================
score: 0.00 / 100
mean_improvement: -2.42%
full_score_improvement: 50.00%

build_improvement: 4.51%
  build_ik_all_sec: baseline=35.2836, current=32.767, improvement=7.13%
  build_ik_content_sec: baseline=28.3764, current=26.832, improvement=5.44%
  build_beng_en_sec: baseline=14.7578, current=14.617, improvement=0.95%
tokenize_improvement: -12.51%
  tokenize_ik_avg_ms: baseline=0.76478, current=0.8587, improvement=-12.28%
  tokenize_beng_avg_ms: baseline=0.42262, current=0.4765, improvement=-12.75%
query_improvement: 0.75%
  query_cn_avg_ms: baseline=16.6628, current=16.5968, improvement=0.40%
  query_beng_avg_ms: baseline=24.3042, current=24.161, improvement=0.59%
  query_mixed_avg_ms: baseline=17.5593, current=17.4775, improvement=0.47%
  query_limit_avg_ms: baseline=16.2334, current=15.985, improvement=1.53%

FTS Large Benchmark Report

========================================
FTS Large Benchmark Report
========================================
timestamp:              2026-07-15 08:27:04
label:                  vldb-ci-29398698650-1
git_head:               b7ee6c7
git_dirty:              0
rows:                   20000
batch:                  500
rounds:                 3000
query_rounds:           200
samples:                3
warmup:                 30
skip_load:              0
----------------------------------------
select1_avg_ms:         0.2732
select1_stdev_ms:       0.0035
raw_load_sec:           1.486
raw_load_rows_per_sec:  13459.0
build_ik_all_sec:       32.767
build_ik_content_sec:   26.832
build_beng_en_sec:      14.617
build_total_sec:        74.230
----------------------------------------
tokenize_ik_avg_ms:     0.8587
tokenize_ik_median_ms:  0.8596
tokenize_ik_stdev_ms:   0.0020
tokenize_beng_avg_ms:   0.4765
tokenize_beng_median_ms:0.4756
tokenize_beng_stdev_ms: 0.0016
----------------------------------------
query_cn_hits:          8001
query_cn_avg_ms:        16.5968
query_cn_stdev_ms:      0.0153
query_beng_hits:        11000
query_beng_avg_ms:      24.1610
query_beng_stdev_ms:    0.0212
query_mixed_hits:       7332
query_mixed_avg_ms:     17.4775
query_mixed_stdev_ms:   0.0729
query_limit_hits:       20
query_limit_avg_ms:     15.9850
query_limit_stdev_ms:   0.0137
========================================

Workflow run