test(chunk): regenerate AST + long-section snapshots for V009 chunk field

S3 의 Chunk struct 갱신 (kebab-core 의 tokenized_korean_text:
Option<String> field 추가) 가 모든 chunk snapshot JSON 의 serde
serialize 결과를 변경시킴. 10 snapshot fixture (9 AST chunker +
markdown long-section) 의 baseline 을 V009 형태로 regenerate.

각 snapshot 의 변경 = chunk JSON 마다 `"tokenized_korean_text":
null` field 추가 (대부분의 fixture 가 영어 코드라 lindera 의 None
fallback). 동작 변경 없음 — serde representation 의 cascade만.

Spec: docs/superpowers/specs/2026-05-28-v0.20.x-korean-morphological-tokenizer-spec.md §6.2
Plan: docs/superpowers/plans/2026-05-28-v0.20.x-korean-morphological-tokenizer-plan.md (S3 follow-up via S11 sanity)

crates/kebab-chunk/tests/fixtures/code-sample.c.chunks.snapshot.json

@@ -18,7 +18,8 @@
       }
     ],
     "text": "#include <stdio.h>\n#include <stdlib.h>\n\n#define MAX_BUF 4096\n\ntypedef enum {\n    OK = 0,\n    ERR_PARSE,\n    ERR_IO,\n} status_t;\n\ntypedef struct {\n    int id;\n    char name[64];\n    status_t status;\n} record_t;\n\nstatic int counter = 0;",
-    "token_estimate": 78
+    "token_estimate": 78,
+    "tokenized_korean_text": "# include < stdio . h > # include < stdlib . h > # define MAX _ BUF 4096 typedef enum { OK = 0 , ERR _ PARSE , ERR _ IO , } status _ t ; typedef struct { int id ; char name [ 64 ]; status _ t status ; } record _ t ; static int counter = 0 ;"
   },
   {
     "block_ids": [
@@ -39,7 +40,8 @@
       }
     ],
     "text": "int parse_record(const char *line, record_t *out) {\n    if (line == NULL || out == NULL) return ERR_PARSE;\n    return OK;\n}",
-    "token_estimate": 41
+    "token_estimate": 41,
+    "tokenized_korean_text": "int parse _ record ( const char * line , record _ t * out ) { if ( line == NULL || out == NULL ) return ERR _ PARSE ; return OK ; }"
   },
   {
     "block_ids": [
@@ -60,7 +62,8 @@
       }
     ],
     "text": "void print_record(const record_t *r) {\n    printf(\"[%d] %s (status=%d)\\n\", r->id, r->name, r->status);\n}",
-    "token_estimate": 35
+    "token_estimate": 35,
+    "tokenized_korean_text": "void print _ record ( const record _ t * r ) { printf (\"[% d ] % s ( status =% d )\\ n \", r -> id , r -> name , r -> status ); }"
   },
   {
     "block_ids": [
@@ -81,6 +84,7 @@
       }
     ],
     "text": "int main(void) {\n    record_t r = { .id = 1, .name = \"foo\", .status = OK };\n    print_record(&r);\n    return 0;\n}",
-    "token_estimate": 38
+    "token_estimate": 38,
+    "tokenized_korean_text": "int main ( void ) { record _ t r = { . id = 1 , . name = \" foo \", . status = OK }; print _ record (& r ); return 0 ; }"
   }
 ]

crates/kebab-chunk/tests/fixtures/code-sample.cpp.chunks.snapshot.json

@@ -18,7 +18,8 @@
       }
     ],
     "text": "#include <string>\n#include <vector>\n\nnamespace kebab {",
-    "token_estimate": 18
+    "token_estimate": 18,
+    "tokenized_korean_text": "# include < string > # include < vector > namespace kebab {"
   },
   {
     "block_ids": [
@@ -39,7 +40,8 @@
       }
     ],
     "text": "class MdHeadingV1Chunker {\npublic:\n    MdHeadingV1Chunker() = default;\n    ~MdHeadingV1Chunker() = default;\n\n    std::string chunk_doc(const std::string& doc) {\n        return doc;\n    }\n\n    int operator()(int x) const {\n        return x * 2;\n    }\n\nprivate:\n    int counter_ = 0;\n};",
-    "token_estimate": 95
+    "token_estimate": 95,
+    "tokenized_korean_text": "class MdHeadingV 1 Chunker { public : MdHeadingV 1 Chunker ( ) = default ; ~ MdHeadingV 1 Chunker ( ) = default ; std : : string chunk _ doc ( const std : : string & doc ) { return doc ; } int operator ( ) ( int x ) const { return x * 2 ; } private : int counter _ = 0 ; };"
   },
   {
     "block_ids": [
@@ -60,7 +62,8 @@
       }
     ],
     "text": "template <typename T>\nT identity(T value) {\n    return value;\n}",
-    "token_estimate": 21
+    "token_estimate": 21,
+    "tokenized_korean_text": "template < typename T > T identity ( T value ) { return value ; }"
   },
   {
     "block_ids": [
@@ -81,7 +84,8 @@
       }
     ],
     "text": "void global_helper() {\n    // free function in kebab namespace\n}",
-    "token_estimate": 22
+    "token_estimate": 22,
+    "tokenized_korean_text": "void global _ helper ( ) { / / free function in kebab namespace }"
   },
   {
     "block_ids": [
@@ -102,6 +106,7 @@
       }
     ],
     "text": "int main() {\n    kebab::chunk::MdHeadingV1Chunker c;\n    return 0;\n}",
-    "token_estimate": 23
+    "token_estimate": 23,
+    "tokenized_korean_text": "int main ( ) { kebab : : chunk : : MdHeadingV 1 Chunker c ; return 0 ; }"
   }
 ]

crates/kebab-chunk/tests/fixtures/code-sample.go.chunks.snapshot.json

@@ -18,7 +18,8 @@
       }
     ],
     "text": "import (\n\t\"fmt\"\n\t\"os\"\n\t\"strings\"\n)",
-    "token_estimate": 12
+    "token_estimate": 12,
+    "tokenized_korean_text": "import ( \" fmt \" \" os \" \" strings \" )"
   },
   {
     "block_ids": [
@@ -39,7 +40,8 @@
       }
     ],
     "text": "func ComputeMRR(scores []float64) float64 {\n\tif len(scores) == 0 {\n\t\treturn 0.0\n\t}\n\t_ = fmt.Sprintf(\"%v\", scores)\n\treturn 1.0 / float64(len(scores))\n}",
-    "token_estimate": 50
+    "token_estimate": 50,
+    "tokenized_korean_text": "func ComputeMRR ( scores [ ] float 64 ) float 64 { if len ( scores ) == 0 { return 0 . 0 } _ = fmt . Sprintf (\"% v \", scores ) return 1 . 0 / float 64 ( len ( scores ) ) }"
   },
   {
     "block_ids": [
@@ -60,7 +62,8 @@
       }
     ],
     "text": "type MetricsCollector struct {\n\tScores []float64\n\tLabels []string\n\tCounts map[string]int\n\tTotals map[string]float64\n\tTags   []string\n}",
-    "token_estimate": 45
+    "token_estimate": 45,
+    "tokenized_korean_text": "type MetricsCollector struct { Scores [ ] float 64 Labels [ ] string Counts map [ string ] int Totals map [ string ] float 64 Tags [ ] string }"
   },
   {
     "block_ids": [
@@ -81,7 +84,8 @@
       }
     ],
     "text": "type BaseEvaluator struct {\n\tName string\n}\n\nfunc (e *BaseEvaluator) Evaluate(data []string) error {\n\t_ = os.Stderr\n\t_ = strings.Join(data, \",\")\n\treturn nil\n}",
-    "token_estimate": 53
+    "token_estimate": 53,
+    "tokenized_korean_text": "type BaseEvaluator struct { Name string } func ( e * BaseEvaluator ) Evaluate ( data [ ] string ) error { _ = os . Stderr _ = strings . Join ( data , \",\") return nil }"
   },
   {
     "block_ids": [
@@ -102,7 +106,8 @@
       }
     ],
     "text": "func (m *MetricsCollector) Run(inputs []float64) {\n\tfor _, inp := range inputs {\n\t\tm.Scores = append(\n\t\t\tm.Scores,\n\t\t\tinp,\n\t\t)\n\t}\n}",
-    "token_estimate": 44
+    "token_estimate": 44,
+    "tokenized_korean_text": "func ( m * MetricsCollector ) Run ( inputs [ ] float 64 ) { for _, inp := range inputs { m . Scores = append ( m . Scores , inp , ) } }"
   },
   {
     "block_ids": [
@@ -123,7 +128,8 @@
       }
     ],
     "text": "func (m *MetricsCollector) Report() map[string]interface{} {\n\treturn map[string]interface{}{\n\t\t\"mean\":  0.0,\n\t\t\"count\": len(m.Scores),\n\t\t\"tags\":  m.Tags,\n\t}\n}",
-    "token_estimate": 53
+    "token_estimate": 53,
+    "tokenized_korean_text": "func ( m * MetricsCollector ) Report ( ) map [ string ] interface {} { return map [ string ] interface {}{ \" mean \": 0 . 0 , \" count \": len ( m . Scores ) , \" tags \": m . Tags , } }"
   },
   {
     "block_ids": [
@@ -144,7 +150,8 @@
       }
     ],
     "text": "func BigCompute(data []int) int {\n\tv0 := 0\n\tif 0 < len(data) {\n\t\tv0 = data[0]\n\t}\n\tv1 := 0\n\tif 1 < len(data) {\n\t\tv1 = data[1]\n\t}\n\tv2 := 0\n\tif 2 < len(data) {\n\t\tv2 = data[2]\n\t}\n\tv3 := 0\n\tif 3 < len(data) {\n\t\tv3 = data[3]\n\t}\n\tv4 := 0\n\tif 4 < len(data) {\n\t\tv4 = data[4]\n\t}\n\tv5 := 0\n\tif 5 < len(data) {\n\t\tv5 = data[5]\n\t}\n\tv6 := 0\n\tif 6 < len(data) {\n\t\tv6 = data[6]\n\t}\n\tv7 := 0\n\tif 7 < len(data) {\n\t\tv7 = data[7]\n\t}\n\tv8 := 0\n\tif 8 < len(data) {\n\t\tv8 = data[8]\n\t}\n\tv9 := 0\n\tif 9 < len(data) {\n\t\tv9 = data[9]\n\t}\n\tv10 := 0\n\tif 10 < len(data) {\n\t\tv10 = data[10]\n\t}\n\tv11 := 0\n\tif 11 < len(data) {\n\t\tv11 = data[11]\n\t}\n\tv12 := 0\n\tif 12 < len(data) {\n\t\tv12 = data[12]\n\t}\n\tv13 := 0\n\tif 13 < len(data) {\n\t\tv13 = data[13]\n\t}\n\tv14 := 0\n\tif 14 < len(data) {\n\t\tv14 = data[14]\n\t}\n\tv15 := 0\n\tif 15 < len(data) {\n\t\tv15 = data[15]\n\t}\n\tv16 := 0\n\tif 16 < len(data) {\n\t\tv16 = data[16]\n\t}\n\tv17 := 0\n\tif 17 < len(data) {\n\t\tv17 = data[17]\n\t}\n\tv18 := 0\n\tif 18 < len(data) {\n\t\tv18 = data[18]\n\t}\n\tv19 := 0\n\tif 19 < len(data) {\n\t\tv19 = data[19]\n\t}\n\tv20 := 0\n\tif 20 < len(data) {\n\t\tv20 = data[20]\n\t}\n\tv21 := 0\n\tif 21 < len(data) {\n\t\tv21 = data[21]\n\t}\n\tv22 := 0\n\tif 22 < len(data) {\n\t\tv22 = data[22]\n\t}\n\tv23 := 0\n\tif 23 < len(data) {\n\t\tv23 = data[23]\n\t}\n\tv24 := 0\n\tif 24 < len(data) {\n\t\tv24 = data[24]\n\t}\n\tv25 := 0\n\tif 25 < len(data) {\n\t\tv25 = data[25]\n\t}\n\tv26 := 0\n\tif 26 < len(data) {\n\t\tv26 = data[26]\n\t}\n\tv27 := 0\n\tif 27 < len(data) {\n\t\tv27 = data[27]\n\t}\n\tv28 := 0\n\tif 28 < len(data) {\n\t\tv28 = data[28]\n\t}\n\tv29 := 0\n\tif 29 < len(data) {\n\t\tv29 = data[29]\n\t}\n\tv30 := 0\n\tif 30 < len(data) {\n\t\tv30 = data[30]\n\t}\n\tv31 := 0\n\tif 31 < len(data) {\n\t\tv31 = data[31]\n\t}\n\tv32 := 0\n\tif 32 < len(data) {\n\t\tv32 = data[32]\n\t}\n\tv33 := 0\n\tif 33 < len(data) {\n\t\tv33 = data[33]\n\t}\n\tv34 := 0\n\tif 34 < len(data) {\n\t\tv34 = data[34]\n\t}\n\tv35 := 0\n\tif 35 < len(data) {\n\t\tv35 = data[35]\n\t}\n\tv36 := 0\n\tif 36 < len(data) {\n\t\tv36 = data[36]\n\t}\n\tv37 := 0\n\tif 37 < len(data) {\n\t\tv37 = data[37]\n\t}\n\tv38 := 0\n\tif 38 < len(data) {\n\t\tv38 = data[38]\n\t}\n\tv39 := 0\n\tif 39 < len(data) {\n\t\tv39 = data[39]\n\t}\n\tv40 := 0\n\tif 40 < len(data) {\n\t\tv40 = data[40]\n\t}\n\tv41 := 0\n\tif 41 < len(data) {\n\t\tv41 = data[41]\n\t}\n\tv42 := 0\n\tif 42 < len(data) {\n\t\tv42 = data[42]\n\t}\n\tv43 := 0\n\tif 43 < len(data) {\n\t\tv43 = data[43]\n\t}\n\tv44 := 0\n\tif 44 < len(data) {\n\t\tv44 = data[44]\n\t}\n\tv45 := 0\n\tif 45 < len(data) {\n\t\tv45 = data[45]\n\t}\n\tv46 := 0\n\tif 46 < len(data) {\n\t\tv46 = data[46]\n\t}\n\tv47 := 0\n\tif 47 < len(data) {\n\t\tv47 = data[47]\n\t}\n\tv48 := 0\n\tif 48 < len(data) {\n\t\tv48 = data[48]\n\t}\n\tv49 := 0\n\tif 49 < len(data) {\n\t\tv49 = data[49]",
-    "token_estimate": 847
+    "token_estimate": 847,
+    "tokenized_korean_text": "func BigCompute ( data [ ] int ) int { v 0 := 0 if 0 < len ( data ) { v 0 = data [ 0 ] } v 1 := 0 if 1 < len ( data ) { v 1 = data [ 1 ] } v 2 := 0 if 2 < len ( data ) { v 2 = data [ 2 ] } v 3 := 0 if 3 < len ( data ) { v 3 = data [ 3 ] } v 4 := 0 if 4 < len ( data ) { v 4 = data [ 4 ] } v 5 := 0 if 5 < len ( data ) { v 5 = data [ 5 ] } v 6 := 0 if 6 < len ( data ) { v 6 = data [ 6 ] } v 7 := 0 if 7 < len ( data ) { v 7 = data [ 7 ] } v 8 := 0 if 8 < len ( data ) { v 8 = data [ 8 ] } v 9 := 0 if 9 < len ( data ) { v 9 = data [ 9 ] } v 10 := 0 if 10 < len ( data ) { v 10 = data [ 10 ] } v 11 := 0 if 11 < len ( data ) { v 11 = data [ 11 ] } v 12 := 0 if 12 < len ( data ) { v 12 = data [ 12 ] } v 13 := 0 if 13 < len ( data ) { v 13 = data [ 13 ] } v 14 := 0 if 14 < len ( data ) { v 14 = data [ 14 ] } v 15 := 0 if 15 < len ( data ) { v 15 = data [ 15 ] } v 16 := 0 if 16 < len ( data ) { v 16 = data [ 16 ] } v 17 := 0 if 17 < len ( data ) { v 17 = data [ 17 ] } v 18 := 0 if 18 < len ( data ) { v 18 = data [ 18 ] } v 19 := 0 if 19 < len ( data ) { v 19 = data [ 19 ] } v 20 := 0 if 20 < len ( data ) { v 20 = data [ 20 ] } v 21 := 0 if 21 < len ( data ) { v 21 = data [ 21 ] } v 22 := 0 if 22 < len ( data ) { v 22 = data [ 22 ] } v 23 := 0 if 23 < len ( data ) { v 23 = data [ 23 ] } v 24 := 0 if 24 < len ( data ) { v 24 = data [ 24 ] } v 25 := 0 if 25 < len ( data ) { v 25 = data [ 25 ] } v 26 := 0 if 26 < len ( data ) { v 26 = data [ 26 ] } v 27 := 0 if 27 < len ( data ) { v 27 = data [ 27 ] } v 28 := 0 if 28 < len ( data ) { v 28 = data [ 28 ] } v 29 := 0 if 29 < len ( data ) { v 29 = data [ 29 ] } v 30 := 0 if 30 < len ( data ) { v 30 = data [ 30 ] } v 31 := 0 if 31 < len ( data ) { v 31 = data [ 31 ] } v 32 := 0 if 32 < len ( data ) { v 32 = data [ 32 ] } v 33 := 0 if 33 < len ( data ) { v 33 = data [ 33 ] } v 34 := 0 if 34 < len ( data ) { v 34 = data [ 34 ] } v 35 := 0 if 35 < len ( data ) { v 35 = data [ 35 ] } v 36 := 0 if 36 < len ( data ) { v 36 = data [ 36 ] } v 37 := 0 if 37 < len ( data ) { v 37 = data [ 37 ] } v 38 := 0 if 38 < len ( data ) { v 38 = data [ 38 ] } v 39 := 0 if 39 < len ( data ) { v 39 = data [ 39 ] } v 40 := 0 if 40 < len ( data ) { v 40 = data [ 40 ] } v 41 := 0 if 41 < len ( data ) { v 41 = data [ 41 ] } v 42 := 0 if 42 < len ( data ) { v 42 = data [ 42 ] } v 43 := 0 if 43 < len ( data ) { v 43 = data [ 43 ] } v 44 := 0 if 44 < len ( data ) { v 44 = data [ 44 ] } v 45 := 0 if 45 < len ( data ) { v 45 = data [ 45 ] } v 46 := 0 if 46 < len ( data ) { v 46 = data [ 46 ] } v 47 := 0 if 47 < len ( data ) { v 47 = data [ 47 ] } v 48 := 0 if 48 < len ( data ) { v 48 = data [ 48 ] } v 49 := 0 if 49 < len ( data ) { v 49 = data [ 49 ]"
   },
   {
     "block_ids": [
@@ -165,7 +172,8 @@
       }
     ],
     "text": "\t}\n\tv50 := 0\n\tif 50 < len(data) {\n\t\tv50 = data[50]\n\t}\n\tv51 := 0\n\tif 51 < len(data) {\n\t\tv51 = data[51]\n\t}\n\tv52 := 0\n\tif 52 < len(data) {\n\t\tv52 = data[52]\n\t}\n\tv53 := 0\n\tif 53 < len(data) {\n\t\tv53 = data[53]\n\t}\n\tv54 := 0\n\tif 54 < len(data) {\n\t\tv54 = data[54]\n\t}\n\tv55 := 0\n\tif 55 < len(data) {\n\t\tv55 = data[55]\n\t}\n\tv56 := 0\n\tif 56 < len(data) {\n\t\tv56 = data[56]\n\t}\n\tv57 := 0\n\tif 57 < len(data) {\n\t\tv57 = data[57]\n\t}\n\tv58 := 0\n\tif 58 < len(data) {\n\t\tv58 = data[58]\n\t}\n\tv59 := 0\n\tif 59 < len(data) {\n\t\tv59 = data[59]\n\t}\n\tv60 := 0\n\tif 60 < len(data) {\n\t\tv60 = data[60]\n\t}\n\tv61 := 0\n\tif 61 < len(data) {\n\t\tv61 = data[61]\n\t}\n\tv62 := 0\n\tif 62 < len(data) {\n\t\tv62 = data[62]\n\t}\n\tv63 := 0\n\tif 63 < len(data) {\n\t\tv63 = data[63]\n\t}\n\tv64 := 0\n\tif 64 < len(data) {\n\t\tv64 = data[64]\n\t}\n\tv65 := 0\n\tif 65 < len(data) {\n\t\tv65 = data[65]\n\t}\n\tv66 := 0\n\tif 66 < len(data) {\n\t\tv66 = data[66]\n\t}\n\tv67 := 0\n\tif 67 < len(data) {\n\t\tv67 = data[67]\n\t}\n\tv68 := 0\n\tif 68 < len(data) {\n\t\tv68 = data[68]\n\t}\n\tv69 := 0\n\tif 69 < len(data) {\n\t\tv69 = data[69]\n\t}\n\tv70 := 0\n\tif 70 < len(data) {\n\t\tv70 = data[70]\n\t}\n\tv71 := 0\n\tif 71 < len(data) {\n\t\tv71 = data[71]\n\t}\n\tv72 := 0\n\tif 72 < len(data) {\n\t\tv72 = data[72]\n\t}\n\tv73 := 0\n\tif 73 < len(data) {\n\t\tv73 = data[73]\n\t}\n\tv74 := 0\n\tif 74 < len(data) {\n\t\tv74 = data[74]\n\t}\n\tv75 := 0\n\tif 75 < len(data) {\n\t\tv75 = data[75]\n\t}\n\tv76 := 0\n\tif 76 < len(data) {\n\t\tv76 = data[76]\n\t}\n\tv77 := 0\n\tif 77 < len(data) {\n\t\tv77 = data[77]\n\t}\n\tv78 := 0\n\tif 78 < len(data) {\n\t\tv78 = data[78]\n\t}\n\tv79 := 0\n\tif 79 < len(data) {\n\t\tv79 = data[79]\n\t}\n\tv80 := 0\n\tif 80 < len(data) {\n\t\tv80 = data[80]\n\t}\n\tv81 := 0\n\tif 81 < len(data) {\n\t\tv81 = data[81]\n\t}\n\tv82 := 0\n\tif 82 < len(data) {\n\t\tv82 = data[82]\n\t}\n\tv83 := 0\n\tif 83 < len(data) {\n\t\tv83 = data[83]\n\t}\n\tv84 := 0\n\tif 84 < len(data) {\n\t\tv84 = data[84]\n\t}\n\tv85 := 0\n\tif 85 < len(data) {\n\t\tv85 = data[85]\n\t}\n\tv86 := 0\n\tif 86 < len(data) {\n\t\tv86 = data[86]\n\t}\n\tv87 := 0\n\tif 87 < len(data) {\n\t\tv87 = data[87]\n\t}\n\tv88 := 0\n\tif 88 < len(data) {\n\t\tv88 = data[88]\n\t}\n\tv89 := 0\n\tif 89 < len(data) {\n\t\tv89 = data[89]\n\t}\n\tv90 := 0\n\tif 90 < len(data) {\n\t\tv90 = data[90]\n\t}\n\tv91 := 0\n\tif 91 < len(data) {\n\t\tv91 = data[91]\n\t}\n\tv92 := 0\n\tif 92 < len(data) {\n\t\tv92 = data[92]\n\t}\n\tv93 := 0\n\tif 93 < len(data) {\n\t\tv93 = data[93]\n\t}\n\tv94 := 0\n\tif 94 < len(data) {\n\t\tv94 = data[94]\n\t}\n\tv95 := 0\n\tif 95 < len(data) {\n\t\tv95 = data[95]\n\t}\n\tv96 := 0\n\tif 96 < len(data) {\n\t\tv96 = data[96]\n\t}\n\tv97 := 0\n\tif 97 < len(data) {\n\t\tv97 = data[97]\n\t}\n\tv98 := 0\n\tif 98 < len(data) {\n\t\tv98 = data[98]\n\t}\n\tv99 := 0\n\tif 99 < len(data) {\n\t\tv99 = data[99]",
-    "token_estimate": 850
+    "token_estimate": 850,
+    "tokenized_korean_text": "} v 50 := 0 if 50 < len ( data ) { v 50 = data [ 50 ] } v 51 := 0 if 51 < len ( data ) { v 51 = data [ 51 ] } v 52 := 0 if 52 < len ( data ) { v 52 = data [ 52 ] } v 53 := 0 if 53 < len ( data ) { v 53 = data [ 53 ] } v 54 := 0 if 54 < len ( data ) { v 54 = data [ 54 ] } v 55 := 0 if 55 < len ( data ) { v 55 = data [ 55 ] } v 56 := 0 if 56 < len ( data ) { v 56 = data [ 56 ] } v 57 := 0 if 57 < len ( data ) { v 57 = data [ 57 ] } v 58 := 0 if 58 < len ( data ) { v 58 = data [ 58 ] } v 59 := 0 if 59 < len ( data ) { v 59 = data [ 59 ] } v 60 := 0 if 60 < len ( data ) { v 60 = data [ 60 ] } v 61 := 0 if 61 < len ( data ) { v 61 = data [ 61 ] } v 62 := 0 if 62 < len ( data ) { v 62 = data [ 62 ] } v 63 := 0 if 63 < len ( data ) { v 63 = data [ 63 ] } v 64 := 0 if 64 < len ( data ) { v 64 = data [ 64 ] } v 65 := 0 if 65 < len ( data ) { v 65 = data [ 65 ] } v 66 := 0 if 66 < len ( data ) { v 66 = data [ 66 ] } v 67 := 0 if 67 < len ( data ) { v 67 = data [ 67 ] } v 68 := 0 if 68 < len ( data ) { v 68 = data [ 68 ] } v 69 := 0 if 69 < len ( data ) { v 69 = data [ 69 ] } v 70 := 0 if 70 < len ( data ) { v 70 = data [ 70 ] } v 71 := 0 if 71 < len ( data ) { v 71 = data [ 71 ] } v 72 := 0 if 72 < len ( data ) { v 72 = data [ 72 ] } v 73 := 0 if 73 < len ( data ) { v 73 = data [ 73 ] } v 74 := 0 if 74 < len ( data ) { v 74 = data [ 74 ] } v 75 := 0 if 75 < len ( data ) { v 75 = data [ 75 ] } v 76 := 0 if 76 < len ( data ) { v 76 = data [ 76 ] } v 77 := 0 if 77 < len ( data ) { v 77 = data [ 77 ] } v 78 := 0 if 78 < len ( data ) { v 78 = data [ 78 ] } v 79 := 0 if 79 < len ( data ) { v 79 = data [ 79 ] } v 80 := 0 if 80 < len ( data ) { v 80 = data [ 80 ] } v 81 := 0 if 81 < len ( data ) { v 81 = data [ 81 ] } v 82 := 0 if 82 < len ( data ) { v 82 = data [ 82 ] } v 83 := 0 if 83 < len ( data ) { v 83 = data [ 83 ] } v 84 := 0 if 84 < len ( data ) { v 84 = data [ 84 ] } v 85 := 0 if 85 < len ( data ) { v 85 = data [ 85 ] } v 86 := 0 if 86 < len ( data ) { v 86 = data [ 86 ] } v 87 := 0 if 87 < len ( data ) { v 87 = data [ 87 ] } v 88 := 0 if 88 < len ( data ) { v 88 = data [ 88 ] } v 89 := 0 if 89 < len ( data ) { v 89 = data [ 89 ] } v 90 := 0 if 90 < len ( data ) { v 90 = data [ 90 ] } v 91 := 0 if 91 < len ( data ) { v 91 = data [ 91 ] } v 92 := 0 if 92 < len ( data ) { v 92 = data [ 92 ] } v 93 := 0 if 93 < len ( data ) { v 93 = data [ 93 ] } v 94 := 0 if 94 < len ( data ) { v 94 = data [ 94 ] } v 95 := 0 if 95 < len ( data ) { v 95 = data [ 95 ] } v 96 := 0 if 96 < len ( data ) { v 96 = data [ 96 ] } v 97 := 0 if 97 < len ( data ) { v 97 = data [ 97 ] } v 98 := 0 if 98 < len ( data ) { v 98 = data [ 98 ] } v 99 := 0 if 99 < len ( data ) { v 99 = data [ 99 ]"
   },
   {
     "block_ids": [
@@ -186,7 +194,8 @@
       }
     ],
     "text": "\t}\n\tv100 := 0\n\tif 100 < len(data) {\n\t\tv100 = data[100]\n\t}\n\tv101 := 0\n\tif 101 < len(data) {\n\t\tv101 = data[101]\n\t}\n\tv102 := 0\n\tif 102 < len(data) {\n\t\tv102 = data[102]\n\t}\n\tv103 := 0\n\tif 103 < len(data) {\n\t\tv103 = data[103]\n\t}\n\tv104 := 0\n\tif 104 < len(data) {\n\t\tv104 = data[104]\n\t}\n\tv105 := 0\n\tif 105 < len(data) {\n\t\tv105 = data[105]\n\t}\n\tv106 := 0\n\tif 106 < len(data) {\n\t\tv106 = data[106]\n\t}\n\tv107 := 0\n\tif 107 < len(data) {\n\t\tv107 = data[107]\n\t}\n\tv108 := 0\n\tif 108 < len(data) {\n\t\tv108 = data[108]\n\t}\n\tv109 := 0\n\tif 109 < len(data) {\n\t\tv109 = data[109]\n\t}\n\tv110 := 0\n\tif 110 < len(data) {\n\t\tv110 = data[110]\n\t}\n\tv111 := 0\n\tif 111 < len(data) {\n\t\tv111 = data[111]\n\t}\n\tv112 := 0\n\tif 112 < len(data) {\n\t\tv112 = data[112]\n\t}\n\tv113 := 0\n\tif 113 < len(data) {\n\t\tv113 = data[113]\n\t}\n\tv114 := 0\n\tif 114 < len(data) {\n\t\tv114 = data[114]\n\t}\n\tv115 := 0\n\tif 115 < len(data) {\n\t\tv115 = data[115]\n\t}\n\tv116 := 0\n\tif 116 < len(data) {\n\t\tv116 = data[116]\n\t}\n\tv117 := 0\n\tif 117 < len(data) {\n\t\tv117 = data[117]\n\t}\n\tv118 := 0\n\tif 118 < len(data) {\n\t\tv118 = data[118]\n\t}\n\tv119 := 0\n\tif 119 < len(data) {\n\t\tv119 = data[119]\n\t}\n\tv120 := 0\n\tif 120 < len(data) {\n\t\tv120 = data[120]\n\t}\n\tv121 := 0\n\tif 121 < len(data) {\n\t\tv121 = data[121]\n\t}\n\tv122 := 0\n\tif 122 < len(data) {\n\t\tv122 = data[122]\n\t}\n\tv123 := 0\n\tif 123 < len(data) {\n\t\tv123 = data[123]\n\t}\n\tv124 := 0\n\tif 124 < len(data) {\n\t\tv124 = data[124]\n\t}\n\tv125 := 0\n\tif 125 < len(data) {\n\t\tv125 = data[125]\n\t}\n\tv126 := 0\n\tif 126 < len(data) {\n\t\tv126 = data[126]\n\t}\n\tv127 := 0\n\tif 127 < len(data) {\n\t\tv127 = data[127]\n\t}\n\tv128 := 0\n\tif 128 < len(data) {\n\t\tv128 = data[128]\n\t}\n\tv129 := 0\n\tif 129 < len(data) {\n\t\tv129 = data[129]\n\t}\n\tv130 := 0\n\tif 130 < len(data) {\n\t\tv130 = data[130]\n\t}\n\tv131 := 0\n\tif 131 < len(data) {\n\t\tv131 = data[131]\n\t}\n\tv132 := 0\n\tif 132 < len(data) {\n\t\tv132 = data[132]\n\t}\n\tv133 := 0\n\tif 133 < len(data) {\n\t\tv133 = data[133]\n\t}\n\tv134 := 0\n\tif 134 < len(data) {\n\t\tv134 = data[134]\n\t}\n\tv135 := 0\n\tif 135 < len(data) {\n\t\tv135 = data[135]\n\t}\n\tv136 := 0\n\tif 136 < len(data) {\n\t\tv136 = data[136]\n\t}\n\tv137 := 0\n\tif 137 < len(data) {\n\t\tv137 = data[137]\n\t}\n\tv138 := 0\n\tif 138 < len(data) {\n\t\tv138 = data[138]\n\t}\n\tv139 := 0\n\tif 139 < len(data) {\n\t\tv139 = data[139]\n\t}\n\tv140 := 0\n\tif 140 < len(data) {\n\t\tv140 = data[140]\n\t}\n\tv141 := 0\n\tif 141 < len(data) {\n\t\tv141 = data[141]\n\t}\n\tv142 := 0\n\tif 142 < len(data) {\n\t\tv142 = data[142]\n\t}\n\tv143 := 0\n\tif 143 < len(data) {\n\t\tv143 = data[143]\n\t}\n\tv144 := 0\n\tif 144 < len(data) {\n\t\tv144 = data[144]\n\t}\n\tv145 := 0\n\tif 145 < len(data) {\n\t\tv145 = data[145]\n\t}\n\tv146 := 0\n\tif 146 < len(data) {\n\t\tv146 = data[146]\n\t}\n\tv147 := 0\n\tif 147 < len(data) {\n\t\tv147 = data[147]\n\t}\n\tv148 := 0\n\tif 148 < len(data) {\n\t\tv148 = data[148]\n\t}\n\tv149 := 0\n\tif 149 < len(data) {\n\t\tv149 = data[149]",
-    "token_estimate": 917
+    "token_estimate": 917,
+    "tokenized_korean_text": "} v 100 := 0 if 100 < len ( data ) { v 100 = data [ 100 ] } v 101 := 0 if 101 < len ( data ) { v 101 = data [ 101 ] } v 102 := 0 if 102 < len ( data ) { v 102 = data [ 102 ] } v 103 := 0 if 103 < len ( data ) { v 103 = data [ 103 ] } v 104 := 0 if 104 < len ( data ) { v 104 = data [ 104 ] } v 105 := 0 if 105 < len ( data ) { v 105 = data [ 105 ] } v 106 := 0 if 106 < len ( data ) { v 106 = data [ 106 ] } v 107 := 0 if 107 < len ( data ) { v 107 = data [ 107 ] } v 108 := 0 if 108 < len ( data ) { v 108 = data [ 108 ] } v 109 := 0 if 109 < len ( data ) { v 109 = data [ 109 ] } v 110 := 0 if 110 < len ( data ) { v 110 = data [ 110 ] } v 111 := 0 if 111 < len ( data ) { v 111 = data [ 111 ] } v 112 := 0 if 112 < len ( data ) { v 112 = data [ 112 ] } v 113 := 0 if 113 < len ( data ) { v 113 = data [ 113 ] } v 114 := 0 if 114 < len ( data ) { v 114 = data [ 114 ] } v 115 := 0 if 115 < len ( data ) { v 115 = data [ 115 ] } v 116 := 0 if 116 < len ( data ) { v 116 = data [ 116 ] } v 117 := 0 if 117 < len ( data ) { v 117 = data [ 117 ] } v 118 := 0 if 118 < len ( data ) { v 118 = data [ 118 ] } v 119 := 0 if 119 < len ( data ) { v 119 = data [ 119 ] } v 120 := 0 if 120 < len ( data ) { v 120 = data [ 120 ] } v 121 := 0 if 121 < len ( data ) { v 121 = data [ 121 ] } v 122 := 0 if 122 < len ( data ) { v 122 = data [ 122 ] } v 123 := 0 if 123 < len ( data ) { v 123 = data [ 123 ] } v 124 := 0 if 124 < len ( data ) { v 124 = data [ 124 ] } v 125 := 0 if 125 < len ( data ) { v 125 = data [ 125 ] } v 126 := 0 if 126 < len ( data ) { v 126 = data [ 126 ] } v 127 := 0 if 127 < len ( data ) { v 127 = data [ 127 ] } v 128 := 0 if 128 < len ( data ) { v 128 = data [ 128 ] } v 129 := 0 if 129 < len ( data ) { v 129 = data [ 129 ] } v 130 := 0 if 130 < len ( data ) { v 130 = data [ 130 ] } v 131 := 0 if 131 < len ( data ) { v 131 = data [ 131 ] } v 132 := 0 if 132 < len ( data ) { v 132 = data [ 132 ] } v 133 := 0 if 133 < len ( data ) { v 133 = data [ 133 ] } v 134 := 0 if 134 < len ( data ) { v 134 = data [ 134 ] } v 135 := 0 if 135 < len ( data ) { v 135 = data [ 135 ] } v 136 := 0 if 136 < len ( data ) { v 136 = data [ 136 ] } v 137 := 0 if 137 < len ( data ) { v 137 = data [ 137 ] } v 138 := 0 if 138 < len ( data ) { v 138 = data [ 138 ] } v 139 := 0 if 139 < len ( data ) { v 139 = data [ 139 ] } v 140 := 0 if 140 < len ( data ) { v 140 = data [ 140 ] } v 141 := 0 if 141 < len ( data ) { v 141 = data [ 141 ] } v 142 := 0 if 142 < len ( data ) { v 142 = data [ 142 ] } v 143 := 0 if 143 < len ( data ) { v 143 = data [ 143 ] } v 144 := 0 if 144 < len ( data ) { v 144 = data [ 144 ] } v 145 := 0 if 145 < len ( data ) { v 145 = data [ 145 ] } v 146 := 0 if 146 < len ( data ) { v 146 = data [ 146 ] } v 147 := 0 if 147 < len ( data ) { v 147 = data [ 147 ] } v 148 := 0 if 148 < len ( data ) { v 148 = data [ 148 ] } v 149 := 0 if 149 < len ( data ) { v 149 = data [ 149 ]"
   },
   {
     "block_ids": [
@@ -207,7 +216,8 @@
       }
     ],
     "text": "\t}\n\tv150 := 0\n\tif 150 < len(data) {\n\t\tv150 = data[150]\n\t}\n\tv151 := 0\n\tif 151 < len(data) {\n\t\tv151 = data[151]\n\t}\n\tv152 := 0\n\tif 152 < len(data) {\n\t\tv152 = data[152]\n\t}\n\tv153 := 0\n\tif 153 < len(data) {\n\t\tv153 = data[153]\n\t}\n\tv154 := 0\n\tif 154 < len(data) {\n\t\tv154 = data[154]\n\t}\n\tv155 := 0\n\tif 155 < len(data) {\n\t\tv155 = data[155]\n\t}\n\tv156 := 0\n\tif 156 < len(data) {\n\t\tv156 = data[156]\n\t}\n\tv157 := 0\n\tif 157 < len(data) {\n\t\tv157 = data[157]\n\t}\n\tv158 := 0\n\tif 158 < len(data) {\n\t\tv158 = data[158]\n\t}\n\tv159 := 0\n\tif 159 < len(data) {\n\t\tv159 = data[159]\n\t}\n\tv160 := 0\n\tif 160 < len(data) {\n\t\tv160 = data[160]\n\t}\n\tv161 := 0\n\tif 161 < len(data) {\n\t\tv161 = data[161]\n\t}\n\tv162 := 0\n\tif 162 < len(data) {\n\t\tv162 = data[162]\n\t}\n\tv163 := 0\n\tif 163 < len(data) {\n\t\tv163 = data[163]\n\t}\n\tv164 := 0\n\tif 164 < len(data) {\n\t\tv164 = data[164]\n\t}\n\tv165 := 0\n\tif 165 < len(data) {\n\t\tv165 = data[165]\n\t}\n\tv166 := 0\n\tif 166 < len(data) {\n\t\tv166 = data[166]\n\t}\n\tv167 := 0\n\tif 167 < len(data) {\n\t\tv167 = data[167]\n\t}\n\tv168 := 0\n\tif 168 < len(data) {\n\t\tv168 = data[168]\n\t}\n\tv169 := 0\n\tif 169 < len(data) {\n\t\tv169 = data[169]\n\t}\n\tv170 := 0\n\tif 170 < len(data) {\n\t\tv170 = data[170]\n\t}\n\tv171 := 0\n\tif 171 < len(data) {\n\t\tv171 = data[171]\n\t}\n\tv172 := 0\n\tif 172 < len(data) {\n\t\tv172 = data[172]\n\t}\n\tv173 := 0\n\tif 173 < len(data) {\n\t\tv173 = data[173]\n\t}\n\tv174 := 0\n\tif 174 < len(data) {\n\t\tv174 = data[174]\n\t}\n\tv175 := 0\n\tif 175 < len(data) {\n\t\tv175 = data[175]\n\t}\n\tv176 := 0\n\tif 176 < len(data) {\n\t\tv176 = data[176]\n\t}\n\tv177 := 0\n\tif 177 < len(data) {\n\t\tv177 = data[177]\n\t}\n\tv178 := 0\n\tif 178 < len(data) {\n\t\tv178 = data[178]\n\t}\n\tv179 := 0\n\tif 179 < len(data) {\n\t\tv179 = data[179]\n\t}\n\tv180 := 0\n\tif 180 < len(data) {\n\t\tv180 = data[180]\n\t}\n\tv181 := 0\n\tif 181 < len(data) {\n\t\tv181 = data[181]\n\t}\n\tv182 := 0\n\tif 182 < len(data) {\n\t\tv182 = data[182]\n\t}\n\tv183 := 0\n\tif 183 < len(data) {\n\t\tv183 = data[183]\n\t}\n\tv184 := 0\n\tif 184 < len(data) {\n\t\tv184 = data[184]\n\t}\n\tv185 := 0\n\tif 185 < len(data) {\n\t\tv185 = data[185]\n\t}\n\tv186 := 0\n\tif 186 < len(data) {\n\t\tv186 = data[186]\n\t}\n\tv187 := 0\n\tif 187 < len(data) {\n\t\tv187 = data[187]\n\t}\n\tv188 := 0\n\tif 188 < len(data) {\n\t\tv188 = data[188]\n\t}\n\tv189 := 0\n\tif 189 < len(data) {\n\t\tv189 = data[189]\n\t}\n\tv190 := 0\n\tif 190 < len(data) {\n\t\tv190 = data[190]\n\t}\n\tv191 := 0\n\tif 191 < len(data) {\n\t\tv191 = data[191]\n\t}\n\tv192 := 0\n\tif 192 < len(data) {\n\t\tv192 = data[192]\n\t}\n\tv193 := 0\n\tif 193 < len(data) {\n\t\tv193 = data[193]\n\t}\n\tv194 := 0\n\tif 194 < len(data) {\n\t\tv194 = data[194]\n\t}\n\tv195 := 0\n\tif 195 < len(data) {\n\t\tv195 = data[195]\n\t}\n\tv196 := 0\n\tif 196 < len(data) {\n\t\tv196 = data[196]\n\t}\n\tv197 := 0\n\tif 197 < len(data) {\n\t\tv197 = data[197]\n\t}\n\tv198 := 0\n\tif 198 < len(data) {\n\t\tv198 = data[198]\n\t}\n\tv199 := 0\n\tif 199 < len(data) {\n\t\tv199 = data[199]",
-    "token_estimate": 917
+    "token_estimate": 917,
+    "tokenized_korean_text": "} v 150 := 0 if 150 < len ( data ) { v 150 = data [ 150 ] } v 151 := 0 if 151 < len ( data ) { v 151 = data [ 151 ] } v 152 := 0 if 152 < len ( data ) { v 152 = data [ 152 ] } v 153 := 0 if 153 < len ( data ) { v 153 = data [ 153 ] } v 154 := 0 if 154 < len ( data ) { v 154 = data [ 154 ] } v 155 := 0 if 155 < len ( data ) { v 155 = data [ 155 ] } v 156 := 0 if 156 < len ( data ) { v 156 = data [ 156 ] } v 157 := 0 if 157 < len ( data ) { v 157 = data [ 157 ] } v 158 := 0 if 158 < len ( data ) { v 158 = data [ 158 ] } v 159 := 0 if 159 < len ( data ) { v 159 = data [ 159 ] } v 160 := 0 if 160 < len ( data ) { v 160 = data [ 160 ] } v 161 := 0 if 161 < len ( data ) { v 161 = data [ 161 ] } v 162 := 0 if 162 < len ( data ) { v 162 = data [ 162 ] } v 163 := 0 if 163 < len ( data ) { v 163 = data [ 163 ] } v 164 := 0 if 164 < len ( data ) { v 164 = data [ 164 ] } v 165 := 0 if 165 < len ( data ) { v 165 = data [ 165 ] } v 166 := 0 if 166 < len ( data ) { v 166 = data [ 166 ] } v 167 := 0 if 167 < len ( data ) { v 167 = data [ 167 ] } v 168 := 0 if 168 < len ( data ) { v 168 = data [ 168 ] } v 169 := 0 if 169 < len ( data ) { v 169 = data [ 169 ] } v 170 := 0 if 170 < len ( data ) { v 170 = data [ 170 ] } v 171 := 0 if 171 < len ( data ) { v 171 = data [ 171 ] } v 172 := 0 if 172 < len ( data ) { v 172 = data [ 172 ] } v 173 := 0 if 173 < len ( data ) { v 173 = data [ 173 ] } v 174 := 0 if 174 < len ( data ) { v 174 = data [ 174 ] } v 175 := 0 if 175 < len ( data ) { v 175 = data [ 175 ] } v 176 := 0 if 176 < len ( data ) { v 176 = data [ 176 ] } v 177 := 0 if 177 < len ( data ) { v 177 = data [ 177 ] } v 178 := 0 if 178 < len ( data ) { v 178 = data [ 178 ] } v 179 := 0 if 179 < len ( data ) { v 179 = data [ 179 ] } v 180 := 0 if 180 < len ( data ) { v 180 = data [ 180 ] } v 181 := 0 if 181 < len ( data ) { v 181 = data [ 181 ] } v 182 := 0 if 182 < len ( data ) { v 182 = data [ 182 ] } v 183 := 0 if 183 < len ( data ) { v 183 = data [ 183 ] } v 184 := 0 if 184 < len ( data ) { v 184 = data [ 184 ] } v 185 := 0 if 185 < len ( data ) { v 185 = data [ 185 ] } v 186 := 0 if 186 < len ( data ) { v 186 = data [ 186 ] } v 187 := 0 if 187 < len ( data ) { v 187 = data [ 187 ] } v 188 := 0 if 188 < len ( data ) { v 188 = data [ 188 ] } v 189 := 0 if 189 < len ( data ) { v 189 = data [ 189 ] } v 190 := 0 if 190 < len ( data ) { v 190 = data [ 190 ] } v 191 := 0 if 191 < len ( data ) { v 191 = data [ 191 ] } v 192 := 0 if 192 < len ( data ) { v 192 = data [ 192 ] } v 193 := 0 if 193 < len ( data ) { v 193 = data [ 193 ] } v 194 := 0 if 194 < len ( data ) { v 194 = data [ 194 ] } v 195 := 0 if 195 < len ( data ) { v 195 = data [ 195 ] } v 196 := 0 if 196 < len ( data ) { v 196 = data [ 196 ] } v 197 := 0 if 197 < len ( data ) { v 197 = data [ 197 ] } v 198 := 0 if 198 < len ( data ) { v 198 = data [ 198 ] } v 199 := 0 if 199 < len ( data ) { v 199 = data [ 199 ]"
   },
   {
     "block_ids": [
@@ -228,6 +238,7 @@
       }
     ],
     "text": "\t}\n\tv200 := 0\n\tif 200 < len(data) {\n\t\tv200 = data[200]\n\t}\n\tv201 := 0\n\tif 201 < len(data) {\n\t\tv201 = data[201]\n\t}\n\tv202 := 0\n\tif 202 < len(data) {\n\t\tv202 = data[202]\n\t}\n\tv203 := 0\n\tif 203 < len(data) {\n\t\tv203 = data[203]\n\t}\n\tv204 := 0\n\tif 204 < len(data) {\n\t\tv204 = data[204]\n\t}\n\tv205 := 0\n\tif 205 < len(data) {\n\t\tv205 = data[205]\n\t}\n\tv206 := 0\n\tif 206 < len(data) {\n\t\tv206 = data[206]\n\t}\n\tv207 := 0\n\tif 207 < len(data) {\n\t\tv207 = data[207]\n\t}\n\tv208 := 0\n\tif 208 < len(data) {\n\t\tv208 = data[208]\n\t}\n\tv209 := 0\n\tif 209 < len(data) {\n\t\tv209 = data[209]\n\t}\n\treturn len(data)\n}",
-    "token_estimate": 191
+    "token_estimate": 191,
+    "tokenized_korean_text": "} v 200 := 0 if 200 < len ( data ) { v 200 = data [ 200 ] } v 201 := 0 if 201 < len ( data ) { v 201 = data [ 201 ] } v 202 := 0 if 202 < len ( data ) { v 202 = data [ 202 ] } v 203 := 0 if 203 < len ( data ) { v 203 = data [ 203 ] } v 204 := 0 if 204 < len ( data ) { v 204 = data [ 204 ] } v 205 := 0 if 205 < len ( data ) { v 205 = data [ 205 ] } v 206 := 0 if 206 < len ( data ) { v 206 = data [ 206 ] } v 207 := 0 if 207 < len ( data ) { v 207 = data [ 207 ] } v 208 := 0 if 208 < len ( data ) { v 208 = data [ 208 ] } v 209 := 0 if 209 < len ( data ) { v 209 = data [ 209 ] } return len ( data ) }"
   }
 ]

fixtures/markdown/long-section.chunks.snapshot.json

@@ -30,7 +30,8 @@
       }
     ],
     "text": "Alpha\n\nAlpha intro paragraph one. This first paragraph in the alpha section gives a brief overview of what is to follow and serves as the lead-in for the subsequent material covered under the alpha heading.\n\nAlpha intro paragraph two. The second paragraph extends the discussion with additional sentences, padding out the paragraph so that paragraph-level chunk splitting actually has multiple candidates to consider when deciding where to slice the content stream.",
-    "token_estimate": 155
+    "token_estimate": 155,
+    "tokenized_korean_text": "Alpha Alpha intro paragraph one . This first paragraph in the alpha section gives a brief overview of what is to follow and serves as the lead - in for the subsequent material covered under the alpha heading . Alpha intro paragraph two . The second paragraph extends the discussion with additional sentences , padding out the paragraph so that paragraph - level chunk splitting actually has multiple candidates to consider when deciding where to slice the content stream ."
   },
   {
     "block_ids": [
@@ -58,7 +59,8 @@
       }
     ],
     "text": "Alpha Sub\n\nSome prose under the alpha sub-heading. The nested heading should still be respected as a chunk boundary distinct from the parent alpha heading.",
-    "token_estimate": 52
+    "token_estimate": 52,
+    "tokenized_korean_text": "Alpha Sub Some prose under the alpha sub - heading . The nested heading should still be respected as a chunk boundary distinct from the parent alpha heading ."
   },
   {
     "block_ids": [
@@ -80,7 +82,8 @@
       }
     ],
     "text": "// A code block long enough to easily clear any reasonable target_tokens\n// so the never-split-code-block rule is exercised by this fixture. The\n// rest of the function body is intentional filler: line after line of\n// content that, were the chunker permitted to split it, would exceed\n// the target threshold and force a break in the middle of the snippet.\nfn long_code_example_one() {\n    let mut numbers = Vec::new();\n    for i in 0..10 {\n        numbers.push(i * 2);\n    }\n    let mut total = 0_i64;\n    for n in &numbers {\n        total += *n as i64;\n    }\n    println!(\"total = {total}\");\n}\n\nfn long_code_example_two() {\n    let words = [\"alpha\", \"beta\", \"gamma\", \"delta\", \"epsilon\"];\n    for w in words.iter() {\n        if w.starts_with('a') {\n            println!(\"starts with a: {w}\");\n        } else if w.starts_with('b') {\n            println!(\"starts with b: {w}\");\n        } else if w.starts_with('g') {\n            println!(\"starts with g: {w}\");\n        } else {\n            println!(\"other: {w}\");\n        }\n    }\n}\n\nfn long_code_example_three() {\n    let mut buf = String::new();\n    for ch in \"lorem ipsum dolor sit amet\".chars() {\n        if ch.is_ascii_alphabetic() {\n            buf.push(ch.to_ascii_uppercase());\n        }\n    }\n    println!(\"buf = {buf}\");\n}",
-    "token_estimate": 427
+    "token_estimate": 427,
+    "tokenized_korean_text": "/ / A code block long enough to easily clear any reasonable target _ tokens / / so the never - split - code - block rule is exercised by this fixture . The / / rest of the function body is intentional filler : line after line of / / content that , were the chunker permitted to split it , would exceed / / the target threshold and force a break in the middle of the snippet . fn long _ code _ example _ one ( ) { let mut numbers = Vec : : new (); for i in 0 .. 10 { numbers . push ( i * 2 ); } let mut total = 0 _ i 64 ; for n in & numbers { total += * n as i 64 ; } println !(\" total = { total }\"); } fn long _ code _ example _ two ( ) { let words = [\" alpha \", \" beta \", \" gamma \", \" delta \", \" epsilon \"]; for w in words . iter ( ) { if w . starts _ with (' a ') { println !(\" starts with a : { w }\"); } else if w . starts _ with (' b ') { println !(\" starts with b : { w }\"); } else if w . starts _ with (' g ') { println !(\" starts with g : { w }\"); } else { println !(\" other : { w }\"); } } } fn long _ code _ example _ three ( ) { let mut buf = String : : new (); for ch in \" lorem ipsum dolor sit amet \". chars ( ) { if ch . is _ ascii _ alphabetic ( ) { buf . push ( ch . to _ ascii _ uppercase ()); } } println !(\" buf = { buf }\"); }"
   },
   {
     "block_ids": [
@@ -107,7 +110,8 @@
       }
     ],
     "text": "Beta\n\nBeta paragraph one. The beta section opens with an introductory paragraph that sets up the table appearing further down.",
-    "token_estimate": 42
+    "token_estimate": 42,
+    "tokenized_korean_text": "Beta Beta paragraph one . The beta section opens with an introductory paragraph that sets up the table appearing further down ."
   },
   {
     "block_ids": [
@@ -128,7 +132,8 @@
       }
     ],
     "text": "name | kind | note\none | small | first row\ntwo | medium | second row\nthree | large | third row\nfour | huge | fourth row",
-    "token_estimate": 40
+    "token_estimate": 40,
+    "tokenized_korean_text": "name | kind | note one | small | first row two | medium | second row three | large | third row four | huge | fourth row"
   },
   {
     "block_ids": [
@@ -149,7 +154,8 @@
       }
     ],
     "text": "Beta closing paragraph. After the table we have one more paragraph of prose that anchors the end of the beta section before we move on to gamma.",
-    "token_estimate": 48
+    "token_estimate": 48,
+    "tokenized_korean_text": "Beta closing paragraph . After the table we have one more paragraph of prose that anchors the end of the beta section before we move on to gamma ."
   },
   {
     "block_ids": [
@@ -182,7 +188,8 @@
       }
     ],
     "text": "Gamma\n\nGamma paragraph one. The gamma section is intentionally long to exercise the paragraph-level split with overlap rule when chunking under a single heading without any nested sub-headings to break things up further.\n\nGamma paragraph two. We continue accumulating prose so that the running token estimator climbs steadily and eventually trips the target_tokens threshold, forcing the chunker to emit a chunk and seed the next chunk with overlap from the prior tail.",
-    "token_estimate": 157
+    "token_estimate": 157,
+    "tokenized_korean_text": "Gamma Gamma paragraph one . The gamma section is intentionally long to exercise the paragraph - level split with overlap rule when chunking under a single heading without any nested sub - headings to break things up further . Gamma paragraph two . We continue accumulating prose so that the running token estimator climbs steadily and eventually trips the target _ tokens threshold , forcing the chunker to emit a chunk and seed the next chunk with overlap from the prior tail ."
   },
   {
     "block_ids": [
@@ -209,6 +216,7 @@
       }
     ],
     "text": "Gamma paragraph two. We continue accumulating prose so that the running token estimator climbs steadily and eventually trips the target_tokens threshold, forcing the chunker to emit a chunk and seed the next chunk with overlap from the prior tail.\n\nGamma paragraph three. Yet another paragraph under the gamma heading, padded with words to ensure the byte count clears the threshold and the splitting behaviour shows up unambiguously in the snapshot output.",
-    "token_estimate": 153
+    "token_estimate": 153,
+    "tokenized_korean_text": "Gamma paragraph two . We continue accumulating prose so that the running token estimator climbs steadily and eventually trips the target _ tokens threshold , forcing the chunker to emit a chunk and seed the next chunk with overlap from the prior tail . Gamma paragraph three . Yet another paragraph under the gamma heading , padded with words to ensure the byte count clears the threshold and the splitting behaviour shows up unambiguously in the snapshot output ."
   }
 ]