@peaceroad/markdown-it-strong-ja 0.8.1 → 0.9.1

package/src/token-utils.js

@@ -1,13 +1,14 @@
-const CHAR_ASTERISK = 0x2A // *
-const CHAR_SPACE = 0x20 // ' '
-const CHAR_TAB = 0x09 // '\t'
-const CHAR_NEWLINE = 0x0A // '\n'
-const CHAR_IDEOGRAPHIC_SPACE = 0x3000 // fullwidth space
-const MODE_FLAG_COMPATIBLE = 1 << 0
-const MODE_FLAG_AGGRESSIVE = 1 << 1
+const CHAR_ASTERISK = 0x2A // *
+const CHAR_SPACE = 0x20 // ' '
+const CHAR_TAB = 0x09 // '\t'
+const CHAR_NEWLINE = 0x0A // '\n'
+const CHAR_IDEOGRAPHIC_SPACE = 0x3000 // fullwidth space
+const MODE_FLAG_COMPATIBLE = 1 << 0
+const MODE_FLAG_AGGRESSIVE = 1 << 1
 const MODE_FLAG_JAPANESE_BASE = 1 << 2
 const MODE_FLAG_JAPANESE_PLUS = 1 << 3
 const MODE_FLAG_JAPANESE_ANY = MODE_FLAG_JAPANESE_BASE | MODE_FLAG_JAPANESE_PLUS
+const HAS_OWN = Object.prototype.hasOwnProperty
 const REG_CJK_BREAKS_RULE_NAME = /(^|[_-])cjk_breaks([_-]|$)/
 const VALID_CANONICAL_MODES = new Set([
   'compatible',
@@ -15,25 +16,40 @@ const VALID_CANONICAL_MODES = new Set([
   'japanese-boundary',
   'japanese-boundary-guard'
 ])
-const REG_JAPANESE = /[\p{Script=Hiragana}\p{Script=Katakana}\p{Script=Han}\u3000-\u303F\uFF00-\uFFEF]/u
-const REG_ATTRS = /{[^{}\n!@#%^&*()]+?}$/
-
+const REG_JAPANESE = /[\p{Script=Hiragana}\p{Script=Katakana}\p{Script=Han}\u3000-\u303F\uFF00-\uFFEF]/u
+const REG_ATTRS = /{[^{}\n!@#%^&*()]+?}$/
+
 const isJapaneseChar = (ch) => {
-  if (!ch) return false
-  const code = typeof ch === 'string' ? ch.charCodeAt(0) : ch
-  if (code < 128) return false
-  if (code >= 0x3040 && code <= 0x309F) return true
-  if (code >= 0x30A0 && code <= 0x30FF) return true
-  // Han + CJK punctuation/fullwidth ranges are common hot-path hits.
-  // Keep these as cheap numeric checks before the fallback regex.
-  if (code >= 0x3400 && code <= 0x4DBF) return true
-  if (code >= 0x4E00 && code <= 0x9FFF) return true
-  if (code >= 0xF900 && code <= 0xFAFF) return true
-  if (code >= 0x3000 && code <= 0x303F) return true
-  if (code >= 0xFF00 && code <= 0xFFEF) return true
+  if (!ch) return false
+  const code = typeof ch === 'string' ? ch.charCodeAt(0) : ch
+  if (code < 128) return false
+  if (code >= 0x3040 && code <= 0x309F) return true
+  if (code >= 0x30A0 && code <= 0x30FF) return true
+  // Han + CJK punctuation/fullwidth ranges are common hot-path hits.
+  // Keep these as cheap numeric checks before the fallback regex.
+  if (code >= 0x3400 && code <= 0x4DBF) return true
+  if (code >= 0x4E00 && code <= 0x9FFF) return true
+  if (code >= 0xF900 && code <= 0xFAFF) return true
+  if (code >= 0x3000 && code <= 0x303F) return true
+  if (code >= 0xFF00 && code <= 0xFFEF) return true
   return REG_JAPANESE.test(String.fromCharCode(code))
 }
 
+const isAsciiWordCode = (code) => {
+  return (code >= 0x30 && code <= 0x39) ||
+    (code >= 0x41 && code <= 0x5A) ||
+    (code >= 0x61 && code <= 0x7A)
+}
+
+const isSoftSpaceCode = (code) => {
+  return code === CHAR_SPACE || code === CHAR_TAB || code === CHAR_IDEOGRAPHIC_SPACE
+}
+
+const cloneMap = (map) => {
+  if (!map || !Array.isArray(map)) return null
+  return [map[0], map[1]]
+}
+
 const hasCjkBreaksRule = (md) => {
   if (!md || !md.core || !md.core.ruler || !Array.isArray(md.core.ruler.__rules__)) return false
   if (md.__strongJaHasCjkBreaks === true) return true
@@ -58,7 +74,7 @@ const hasCjkBreaksRule = (md) => {
 const isCjkBreaksRuleName = (name) => {
   return typeof name === 'string' && REG_CJK_BREAKS_RULE_NAME.test(name)
 }
-
+
 const resolveMode = (opt) => {
   const raw = opt && typeof opt.mode === 'string' ? opt.mode : 'japanese'
   const normalized = raw.toLowerCase()
@@ -69,9 +85,9 @@ const resolveMode = (opt) => {
     `mditStrongJa: unknown mode "${raw}". Valid modes: japanese, japanese-boundary, japanese-boundary-guard, aggressive, compatible`
   )
 }
-
-const getModeFlags = (mode) => {
-  switch (mode) {
+
+const getModeFlags = (mode) => {
+  switch (mode) {
     case 'compatible':
       return MODE_FLAG_COMPATIBLE
     case 'aggressive':
@@ -80,26 +96,26 @@ const getModeFlags = (mode) => {
       return MODE_FLAG_JAPANESE_BASE
     case 'japanese-boundary-guard':
       return MODE_FLAG_JAPANESE_PLUS
-    default:
-      return 0
-  }
-}
-
-const deriveModeInfo = (opt) => {
-  if (!opt || typeof opt !== 'object') return opt
-  const rawMode = opt.mode
-  if (opt.__strongJaModeRaw === rawMode &&
-      typeof opt.__strongJaMode === 'string' &&
-      typeof opt.__strongJaModeFlags === 'number') {
-    return opt
-  }
-  const mode = resolveMode(opt)
-  opt.__strongJaModeRaw = rawMode
-  opt.__strongJaMode = mode
-  opt.__strongJaModeFlags = getModeFlags(mode)
-  return opt
-}
-
+    default:
+      return 0
+  }
+}
+
+const deriveModeInfo = (opt) => {
+  if (!opt || typeof opt !== 'object') return opt
+  const rawMode = opt.mode
+  if (opt.__strongJaModeRaw === rawMode &&
+      typeof opt.__strongJaMode === 'string' &&
+      typeof opt.__strongJaModeFlags === 'number') {
+    return opt
+  }
+  const mode = resolveMode(opt)
+  opt.__strongJaModeRaw = rawMode
+  opt.__strongJaMode = mode
+  opt.__strongJaModeFlags = getModeFlags(mode)
+  return opt
+}
+
 const deriveOptionInfo = (opt) => {
   if (!opt || typeof opt !== 'object') return opt
   deriveModeInfo(opt)
@@ -126,114 +142,141 @@ const deriveOptionInfo = (opt) => {
   return opt
 }
 
-const getRuntimeOpt = (state, baseOpt) => {
-  if (!state || !state.env || !state.env.__strongJaTokenOpt) return deriveOptionInfo(baseOpt)
-  const override = state.env.__strongJaTokenOpt
-  if (state.__strongJaTokenRuntimeOpt &&
-      state.__strongJaTokenRuntimeBase === baseOpt &&
-      state.__strongJaTokenRuntimeOverride === override) {
-    return state.__strongJaTokenRuntimeOpt
-  }
-  const merged = { ...baseOpt, ...override }
-  state.__strongJaTokenRuntimeOpt = deriveOptionInfo(merged)
-  state.__strongJaTokenRuntimeBase = baseOpt
-  state.__strongJaTokenRuntimeOverride = override
-  return state.__strongJaTokenRuntimeOpt
-}
-
+const hasRuntimeOverride = (override) => {
+  if (!override || typeof override !== 'object') return false
+  return (HAS_OWN.call(override, 'mode') && override.mode !== undefined) ||
+    (HAS_OWN.call(override, 'postprocess') && override.postprocess !== undefined)
+}
+
+const getRuntimeOpt = (state, baseOpt) => {
+  const override = state && state.env ? state.env.__strongJaTokenOpt : null
+  const hasOverride = hasRuntimeOverride(override)
+  if (state &&
+      state.__strongJaTokenRuntimeOpt &&
+      state.__strongJaTokenRuntimeBase === baseOpt &&
+      state.__strongJaTokenRuntimeOverride === override &&
+      state.__strongJaTokenRuntimeHasOverride === hasOverride) {
+    return state.__strongJaTokenRuntimeOpt
+  }
+  let resolved = deriveOptionInfo(baseOpt)
+  if (hasOverride) {
+    const merged = baseOpt && typeof baseOpt === 'object' ? { ...baseOpt } : {}
+    if (HAS_OWN.call(override, 'mode') && override.mode !== undefined) merged.mode = override.mode
+    if (HAS_OWN.call(override, 'postprocess') && override.postprocess !== undefined) merged.postprocess = override.postprocess
+    resolved = deriveOptionInfo(merged)
+  }
+  if (!state) return resolved
+  state.__strongJaTokenRuntimeOpt = resolved
+  state.__strongJaTokenRuntimeBase = baseOpt
+  state.__strongJaTokenRuntimeOverride = override
+  state.__strongJaTokenRuntimeHasOverride = hasOverride
+  return resolved
+}
+
 const getReferenceCount = (state) => {
   if (!state) return 0
   let referenceCount = state.__strongJaReferenceCount
   if (referenceCount !== undefined) return referenceCount
   const references = state.env && state.env.references
-  referenceCount = references ? Object.keys(references).length : 0
+  if (!references) {
+    state.__strongJaReferenceCount = 0
+    return 0
+  }
+  referenceCount = 0
+  for (const key in references) {
+    if (HAS_OWN.call(references, key)) referenceCount++
+  }
   state.__strongJaReferenceCount = referenceCount
   return referenceCount
 }
 
-function normalizeCoreRulesBeforePostprocess(value) {
-  if (!value) return []
-  const list = Array.isArray(value) ? value : [value]
-  const normalized = []
-  const seen = new Set()
-  for (let idx = 0; idx < list.length; idx++) {
-    const raw = list[idx]
-    if (typeof raw !== 'string') continue
-    const trimmed = raw.trim()
-    if (!trimmed || seen.has(trimmed)) continue
-    seen.add(trimmed)
-    normalized.push(trimmed)
-  }
-  return normalized
-}
-
-function ensureCoreRuleOrder(md, ruleNames, targetRuleName) {
-  if (!md || !md.core || !md.core.ruler) return
-  if (!ruleNames || ruleNames.length === 0) return
-  for (let idx = 0; idx < ruleNames.length; idx++) {
-    moveRuleBefore(md.core.ruler, ruleNames[idx], targetRuleName)
-  }
-}
-
-function moveRuleBefore(ruler, ruleName, beforeName) {
-  if (!ruler || !ruler.__rules__) return
-  const rules = ruler.__rules__
-  let fromIdx = -1
-  let beforeIdx = -1
-  for (let idx = 0; idx < rules.length; idx++) {
-    if (rules[idx].name === ruleName) fromIdx = idx
-    if (rules[idx].name === beforeName) beforeIdx = idx
-    if (fromIdx !== -1 && beforeIdx !== -1) break
-  }
-  // Ensure ruleName is before beforeName; keep existing order if already earlier.
-  if (fromIdx === -1 || beforeIdx === -1 || fromIdx < beforeIdx) return
-
-  const rule = rules.splice(fromIdx, 1)[0]
-  rules.splice(beforeIdx, 0, rule)
-  ruler.__cache__ = null
-}
-
-function moveRuleAfter(ruler, ruleName, afterName) {
-  if (!ruler || !ruler.__rules__) return
-  const rules = ruler.__rules__
-  let fromIdx = -1
-  let afterIdx = -1
-  for (let idx = 0; idx < rules.length; idx++) {
-    if (rules[idx].name === ruleName) fromIdx = idx
-    if (rules[idx].name === afterName) afterIdx = idx
-    if (fromIdx !== -1 && afterIdx !== -1) break
-  }
-  if (fromIdx === -1 || afterIdx === -1 || fromIdx === afterIdx + 1) return
-
-  const rule = rules.splice(fromIdx, 1)[0]
-  const targetIdx = fromIdx < afterIdx ? afterIdx - 1 : afterIdx
-  rules.splice(targetIdx + 1, 0, rule)
-  ruler.__cache__ = null
-}
-
-export {
-  CHAR_ASTERISK,
-  CHAR_SPACE,
-  CHAR_TAB,
-  CHAR_NEWLINE,
-  CHAR_IDEOGRAPHIC_SPACE,
+function normalizeCoreRulesBeforePostprocess(value) {
+  if (!value) return []
+  const list = Array.isArray(value) ? value : [value]
+  const normalized = []
+  const seen = new Set()
+  for (let idx = 0; idx < list.length; idx++) {
+    const raw = list[idx]
+    if (typeof raw !== 'string') continue
+    const trimmed = raw.trim()
+    if (!trimmed || seen.has(trimmed)) continue
+    seen.add(trimmed)
+    normalized.push(trimmed)
+  }
+  return normalized
+}
+
+function ensureCoreRuleOrder(md, ruleNames, targetRuleName) {
+  if (!md || !md.core || !md.core.ruler) return
+  if (!ruleNames || ruleNames.length === 0) return
+  for (let idx = 0; idx < ruleNames.length; idx++) {
+    moveRuleBefore(md.core.ruler, ruleNames[idx], targetRuleName)
+  }
+}
+
+function moveRuleBefore(ruler, ruleName, beforeName) {
+  if (!ruler || !ruler.__rules__) return
+  const rules = ruler.__rules__
+  let fromIdx = -1
+  let beforeIdx = -1
+  for (let idx = 0; idx < rules.length; idx++) {
+    if (rules[idx].name === ruleName) fromIdx = idx
+    if (rules[idx].name === beforeName) beforeIdx = idx
+    if (fromIdx !== -1 && beforeIdx !== -1) break
+  }
+  // Ensure ruleName is before beforeName; keep existing order if already earlier.
+  if (fromIdx === -1 || beforeIdx === -1 || fromIdx < beforeIdx) return
+
+  const rule = rules.splice(fromIdx, 1)[0]
+  rules.splice(beforeIdx, 0, rule)
+  ruler.__cache__ = null
+}
+
+function moveRuleAfter(ruler, ruleName, afterName) {
+  if (!ruler || !ruler.__rules__) return
+  const rules = ruler.__rules__
+  let fromIdx = -1
+  let afterIdx = -1
+  for (let idx = 0; idx < rules.length; idx++) {
+    if (rules[idx].name === ruleName) fromIdx = idx
+    if (rules[idx].name === afterName) afterIdx = idx
+    if (fromIdx !== -1 && afterIdx !== -1) break
+  }
+  if (fromIdx === -1 || afterIdx === -1 || fromIdx === afterIdx + 1) return
+
+  const rule = rules.splice(fromIdx, 1)[0]
+  const targetIdx = fromIdx < afterIdx ? afterIdx - 1 : afterIdx
+  rules.splice(targetIdx + 1, 0, rule)
+  ruler.__cache__ = null
+}
+
+export {
+  CHAR_ASTERISK,
+  CHAR_SPACE,
+  CHAR_TAB,
+  CHAR_NEWLINE,
+  CHAR_IDEOGRAPHIC_SPACE,
   REG_ATTRS,
   isJapaneseChar,
+  isAsciiWordCode,
+  isSoftSpaceCode,
+  cloneMap,
   hasCjkBreaksRule,
   isCjkBreaksRuleName,
   resolveMode,
   getModeFlags,
-  deriveModeInfo,
-  deriveOptionInfo,
-  MODE_FLAG_COMPATIBLE,
-  MODE_FLAG_AGGRESSIVE,
-  MODE_FLAG_JAPANESE_BASE,
-  MODE_FLAG_JAPANESE_PLUS,
+  deriveModeInfo,
+  deriveOptionInfo,
+  hasRuntimeOverride,
+  MODE_FLAG_COMPATIBLE,
+  MODE_FLAG_AGGRESSIVE,
+  MODE_FLAG_JAPANESE_BASE,
+  MODE_FLAG_JAPANESE_PLUS,
   MODE_FLAG_JAPANESE_ANY,
   getRuntimeOpt,
   getReferenceCount,
-  normalizeCoreRulesBeforePostprocess,
-  ensureCoreRuleOrder,
-  moveRuleBefore,
-  moveRuleAfter
-}
+  normalizeCoreRulesBeforePostprocess,
+  ensureCoreRuleOrder,
+  moveRuleBefore,
+  moveRuleAfter
+}