@peaceroad/markdown-it-strong-ja 0.7.0 → 0.7.2

package/index.js

@@ -3,39 +3,39 @@ import { patchScanDelims } from './src/token-core.js'
 import { registerTokenCompat } from './src/token-compat.js'
 import { registerTokenPostprocess } from './src/token-postprocess.js'
 
-const buildNoLinkKey = (opt) => {
+const buildNoLinkCacheKey = (opt) => {
   const mode = resolveMode(opt)
   const mditAttrs = opt && opt.mditAttrs === false ? '0' : '1'
   const mdBreaks = opt && opt.mdBreaks === true ? '1' : '0'
   return `${mode}|${mditAttrs}|${mdBreaks}`
 }
 
-const getNoLinkMd = (md, opt) => {
+const getNoLinkMdInstance = (md, opt) => {
   const baseOpt = opt || md.__strongJaTokenOpt || { mode: 'japanese' }
-  const key = buildNoLinkKey(baseOpt)
+  const key = buildNoLinkCacheKey(baseOpt)
   if (!md.__strongJaTokenNoLinkCache) {
     md.__strongJaTokenNoLinkCache = new Map()
   }
   const cache = md.__strongJaTokenNoLinkCache
   if (cache.has(key)) return cache.get(key)
   const noLink = new md.constructor(md.options)
-  tokenEngine(noLink, { ...baseOpt, _skipPostprocess: true })
+  mditStrongJa(noLink, { ...baseOpt, _skipPostprocess: true })
   noLink.inline.ruler.disable(['link'])
   cache.set(key, noLink)
   return noLink
 }
 
-const tokenEngine = (md, option) => {
+const mditStrongJa = (md, option) => {
   if (option && typeof option.engine === 'string' && option.engine !== 'token') {
     throw new Error('mditStrongJa: legacy engine was removed; use token (default)')
   }
   const opt = {
-    mditAttrs: true,
-    mdBreaks: md.options.breaks,
-    mode: 'japanese',
-    coreRulesBeforePostprocess: [],
-    postprocess: true,
-    patchCorePush: true
+    mditAttrs: true, // assume markdown-it-attrs integration by default
+    mdBreaks: md.options.breaks, // inherit md.options.breaks for compat handling
+    mode: 'japanese', // 'japanese' | 'aggressive' | 'compatible' (pairing behavior)
+    coreRulesBeforePostprocess: [], // e.g. ['cjk_breaks'] to keep rules ahead of postprocess
+    postprocess: true, // enable link/ref reconstruction pass
+    patchCorePush: true // keep restore-softbreaks after late cjk_breaks
   }
   if (option) Object.assign(opt, option)
   opt.hasCjkBreaks = hasCjkBreaksRule(md)
@@ -45,7 +45,7 @@ const tokenEngine = (md, option) => {
   registerTokenCompat(md, opt)
 
   if (!opt._skipPostprocess) {
-    registerTokenPostprocess(md, opt, getNoLinkMd)
+    registerTokenPostprocess(md, opt, getNoLinkMdInstance)
     const rawCoreRules = opt.coreRulesBeforePostprocess
     const hasCoreRuleConfig = Array.isArray(rawCoreRules)
       ? rawCoreRules.length > 0
@@ -59,4 +59,4 @@ const tokenEngine = (md, option) => {
   return md
 }
 
-export default tokenEngine
+export default mditStrongJa

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@peaceroad/markdown-it-strong-ja",
   "description": "This is a plugin for markdown-it. It is an alternative to the standard `**` (strong)  and `*` (em) processing. It also processes strings that cannot be converted by the standard.",
-  "version": "0.7.0",
+  "version": "0.7.2",
   "main": "index.js",
   "type": "module",
   "files": [

package/src/token-compat.js

@@ -7,6 +7,12 @@ import {
   moveRuleAfter
 } from './token-utils.js'
 
+const isAsciiWordCode = (code) => {
+  return (code >= 0x30 && code <= 0x39) ||
+    (code >= 0x41 && code <= 0x5A) ||
+    (code >= 0x61 && code <= 0x7A)
+}
+
 const registerTokenCompat = (md, baseOpt) => {
   const hasTextJoinRule = Array.isArray(md.core?.ruler?.__rules__)
     ? md.core.ruler.__rules__.some((rule) => rule && rule.name === 'text_join')
@@ -43,7 +49,6 @@ const registerTokenCompat = (md, baseOpt) => {
     md.__strongJaTokenSoftbreakSpacingRegistered = true
     const normalizeSoftbreakSpacing = (state) => {
       if (!state) return
-      const opt = getRuntimeOpt(state, baseOpt)
       if (baseOpt.hasCjkBreaks !== true && state.md) {
         baseOpt.hasCjkBreaks = hasCjkBreaksRule(state.md)
       }
@@ -61,20 +66,21 @@ const registerTokenCompat = (md, baseOpt) => {
             break
           }
         }
+        if (!hasEmphasis) continue
         for (let j = 0; j < token.children.length; j++) {
           const child = token.children[j]
           if (!child) continue
           if (child.type === 'softbreak') {
-            if (!hasEmphasis) continue
             const prevToken = token.children[j - 1]
             const nextToken = token.children[j + 1]
             if (!prevToken || !nextToken) continue
             if (prevToken.type !== 'text' || !prevToken.content) continue
             if (nextToken.type !== 'text' || !nextToken.content) continue
-            const prevChar = prevToken.content.slice(-1)
-            const nextChar = nextToken.content.charAt(0)
-            const isAsciiWord = nextChar >= '0' && nextChar <= 'z' && /[A-Za-z0-9]/.test(nextChar)
-            const shouldReplace = isAsciiWord && nextChar !== '{' && nextChar !== '\\' && isJapaneseChar(prevChar) && !isJapaneseChar(nextChar)
+            const prevCharCode = prevToken.content.charCodeAt(prevToken.content.length - 1)
+            const nextCharCode = nextToken.content.charCodeAt(0)
+            const isAsciiWord = isAsciiWordCode(nextCharCode)
+            const shouldReplace = isAsciiWord && nextCharCode !== 0x7B && nextCharCode !== 0x5C &&
+              isJapaneseChar(prevCharCode) && !isJapaneseChar(nextCharCode)
             if (!shouldReplace) continue
             child.type = 'text'
             child.tag = ''
@@ -90,10 +96,11 @@ const registerTokenCompat = (md, baseOpt) => {
           for (let idx = 0; idx < child.content.length; idx++) {
             const ch = child.content[idx]
             if (ch === '\n') {
-              const prevChar = idx > 0 ? child.content[idx - 1] : ''
-              const nextChar = idx + 1 < child.content.length ? child.content[idx + 1] : ''
-              const isAsciiWord = nextChar && nextChar >= '0' && nextChar <= 'z' && /[A-Za-z0-9]/.test(nextChar)
-              const shouldReplace = isAsciiWord && nextChar !== '{' && nextChar !== '\\' && isJapaneseChar(prevChar) && !isJapaneseChar(nextChar)
+              const prevCharCode = idx > 0 ? child.content.charCodeAt(idx - 1) : 0
+              const nextCharCode = idx + 1 < child.content.length ? child.content.charCodeAt(idx + 1) : 0
+              const isAsciiWord = isAsciiWordCode(nextCharCode)
+              const shouldReplace = isAsciiWord && nextCharCode !== 0x7B && nextCharCode !== 0x5C &&
+                isJapaneseChar(prevCharCode) && !isJapaneseChar(nextCharCode)
               if (shouldReplace) {
                 normalized += ' '
                 continue
@@ -128,27 +135,26 @@ const registerTokenCompat = (md, baseOpt) => {
       const token = state.tokens[i]
       if (!token || token.type !== 'inline' || !token.children || token.children.length === 0) continue
       const children = token.children
+      let prevTextCharCode = 0
       for (let j = 0; j < children.length; j++) {
         const child = children[j]
-        if (!child || child.type !== 'text' || child.content !== '') continue
-        let prevChar = ''
-        for (let k = j - 1; k >= 0; k--) {
-          const prev = children[k]
-          if (prev && prev.type === 'text' && prev.content) {
-            prevChar = prev.content.charAt(prev.content.length - 1)
-            break
+        if (!child) continue
+        if (child.type === 'text') {
+          if (child.content === '') {
+            if (!prevTextCharCode || !isJapaneseChar(prevTextCharCode)) continue
+            const next = children[j + 1]
+            if (!next || next.type !== 'text' || !next.content) continue
+            const nextCharCode = next.content.charCodeAt(0)
+            if (nextCharCode !== 0x7B) continue
+            child.type = 'softbreak'
+            child.tag = ''
+            child.content = '\n'
+            child.markup = ''
+            child.info = ''
+            continue
           }
+          prevTextCharCode = child.content.charCodeAt(child.content.length - 1)
         }
-        if (!prevChar || !isJapaneseChar(prevChar)) continue
-        const next = children[j + 1]
-        if (!next || next.type !== 'text' || !next.content) continue
-        const nextChar = next.content.charAt(0)
-        if (nextChar !== '{') continue
-        child.type = 'softbreak'
-        child.tag = ''
-        child.content = '\n'
-        child.markup = ''
-        child.info = ''
       }
     }
   }

package/src/token-postprocess.js

@@ -193,7 +193,7 @@ const fixTailAfterLinkStrongClose = (tokens, md, env) => {
   return false
 }
 
-const registerTokenPostprocess = (md, baseOpt, getNoLinkMd) => {
+const registerTokenPostprocess = (md, baseOpt, getNoLinkMdInstance) => {
   if (md.__strongJaTokenPostprocessRegistered) return
   md.__strongJaTokenPostprocessRegistered = true
   md.core.ruler.after('inline', 'strong_ja_token_postprocess', (state) => {
@@ -217,29 +217,23 @@ const registerTokenPostprocess = (md, baseOpt, getNoLinkMd) => {
       const scanState = { depth: 0, brokenEnd: false }
       for (let j = 0; j < children.length; j++) {
         const child = children[j]
-        if (!child || child.type !== 'text' || !child.content) continue
+        if (!child) continue
+        if (!hasEmphasis &&
+            (child.type === 'strong_open' || child.type === 'strong_close' || child.type === 'em_open' || child.type === 'em_close')) {
+          hasEmphasis = true
+        }
+        if (!hasLinkClose && child.type === 'link_close') {
+          hasLinkClose = true
+        }
+        if (child.type !== 'text' || !child.content) continue
+        if (!hasBracketText && (child.content.indexOf('[') !== -1 || child.content.indexOf(']') !== -1)) {
+          hasBracketText = true
+        }
         if (scanBrokenRefState(child.content, scanState).brokenEnd) {
           maxReparse++
         }
       }
-      if (maxReparse === 0) {
-        for (let j = 0; j < children.length; j++) {
-          const child = children[j]
-          if (!child) continue
-          if (child.type === 'text' && child.content) {
-            if (!hasBracketText && (child.content.indexOf('[') !== -1 || child.content.indexOf(']') !== -1)) {
-              hasBracketText = true
-            }
-          }
-          if (!hasEmphasis &&
-              (child.type === 'strong_open' || child.type === 'strong_close' || child.type === 'em_open' || child.type === 'em_close')) {
-            hasEmphasis = true
-          }
-          if (!hasLinkClose && child.type === 'link_close') {
-            hasLinkClose = true
-          }
-        }
-      } else {
+      if (maxReparse !== 0) {
         let allowReparse = true
         while (true) {
           let didReparse = false
@@ -288,7 +282,7 @@ const registerTokenPostprocess = (md, baseOpt, getNoLinkMd) => {
                 if (shouldReparseSegment(children, brokenRefStart, closeIdx)) {
                   const originalMap = getMapFromTokenRange(children, brokenRefStart, closeIdx)
                   const raw = buildRawFromTokens(children, brokenRefStart, closeIdx)
-                  const noLink = getNoLinkMd(md, opt)
+                  const noLink = getNoLinkMdInstance(md, opt)
                   const parsed = parseInlineWithFixes(noLink, raw, state.env)
                   if (parsed && parsed.length > 0) {
                     if (originalMap) {