@peaceroad/markdown-it-strong-ja 0.7.1 → 0.8.0

package/index.js

@@ -1,62 +1,32 @@
-import { hasCjkBreaksRule, normalizeCoreRulesBeforePostprocess, ensureCoreRuleOrder, resolveMode } from './src/token-utils.js'
+import { hasCjkBreaksRule, normalizeCoreRulesBeforePostprocess, ensureCoreRuleOrder, deriveModeInfo } from './src/token-utils.js'
 import { patchScanDelims } from './src/token-core.js'
 import { registerTokenCompat } from './src/token-compat.js'
 import { registerTokenPostprocess } from './src/token-postprocess.js'
 
-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 getNoLinkMdInstance = (md, opt) => {
-  const baseOpt = opt || md.__strongJaTokenOpt || { mode: 'japanese' }
-  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)
-  mditStrongJa(noLink, { ...baseOpt, _skipPostprocess: true })
-  noLink.inline.ruler.disable(['link'])
-  cache.set(key, noLink)
-  return noLink
-}
-
 const mditStrongJa = (md, option) => {
-  if (option && typeof option.engine === 'string' && option.engine !== 'token') {
-    throw new Error('mditStrongJa: legacy engine was removed; use token (default)')
-  }
+  if (option && typeof option.engine === 'string' && option.engine !== 'token') {
+    throw new Error('mditStrongJa: legacy engine was removed; use token (default)')
+  }
   const opt = {
     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)
-
+    mode: 'japanese', // 'japanese'(->japanese-boundary-guard) | 'japanese-boundary' | 'japanese-boundary-guard' | 'aggressive' | 'compatible'
+    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)
+  deriveModeInfo(opt)
+
   md.__strongJaTokenOpt = opt
   patchScanDelims(md)
   registerTokenCompat(md, opt)
 
-  if (!opt._skipPostprocess) {
-    registerTokenPostprocess(md, opt, getNoLinkMdInstance)
-    const rawCoreRules = opt.coreRulesBeforePostprocess
-    const hasCoreRuleConfig = Array.isArray(rawCoreRules)
-      ? rawCoreRules.length > 0
-      : !!rawCoreRules
-    const coreRulesBeforePostprocess = hasCoreRuleConfig
-      ? normalizeCoreRulesBeforePostprocess(rawCoreRules)
-      : []
-    ensureCoreRuleOrder(md, coreRulesBeforePostprocess, 'strong_ja_token_postprocess')
-  }
+  registerTokenPostprocess(md, opt)
+  const coreRulesBeforePostprocess = normalizeCoreRulesBeforePostprocess(opt.coreRulesBeforePostprocess)
+  ensureCoreRuleOrder(md, coreRulesBeforePostprocess, 'strong_ja_token_postprocess')
 
   return md
 }
-
-export default mditStrongJa
+
+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": "0.7.1",
+  "version": "0.8.0",
   "main": "index.js",
   "type": "module",
   "files": [
@@ -11,7 +11,22 @@
     "LICENSE"
   ],
   "scripts": {
-    "test": "node test/test.js"
+    "test": "node test/test.js",
+    "test:fixtures": "node test/test-fixtures.js",
+    "test:edge": "node test/test-edge.js",
+    "test:postprocess": "node test/post-processing.test.js",
+    "test:postprocess-fastpath": "node test/post-processing-fastpath.test.js",
+    "test:postprocess-fastpath-roster": "node test/post-processing-fastpath-roster.test.js",
+    "test:postprocess-flow": "node test/post-processing-flow.test.js",
+    "test:postprocess-gate": "node test/postprocess-gate.js",
+    "test:tokenonly-progress": "node test/post-processing-progress.test.js",
+    "test:readme": "node test/test-readme.js",
+    "test:map": "node test/test-map.js",
+    "test:all": "node test/test-all.js",
+    "bench:scan": "node test/material/perf-scan-delims.mjs",
+    "bench:postprocess": "node test/material/perf-postprocess.mjs",
+    "analyze:postprocess-calls": "node test/material/analyze-postprocess-calls.mjs",
+    "analyze:fastpath": "node test/material/analyze-fastpath-hits.mjs"
   },
   "repository": "https://github.com/peaceroad/p7d-markdown-it-strong-ja.git",
   "author": "peaceroad <peaceroad@gmail.com>",
@@ -20,10 +35,13 @@
     "markdown-it": "^14.1.0"
   },
   "devDependencies": {
-    "@peaceroad/markdown-it-cjk-breaks-mod": "^0.1.5",
-    "@peaceroad/markdown-it-hr-sandwiched-semantic-container": "^0.8.2",
+    "@peaceroad/markdown-it-cjk-breaks-mod": "^0.1.7",
+    "@peaceroad/markdown-it-hr-sandwiched-semantic-container": "^0.8.5",
+    "@peaceroad/markdown-it-renderer-image": "^0.10.0",
+    "@peaceroad/markdown-it-renderer-inline-text": "^0.6.0",
     "markdown-it-attrs": "^4.3.1",
     "markdown-it-sub": "^2.0.0",
-    "markdown-it-sup": "^2.0.0"
+    "markdown-it-sup": "^2.0.0",
+    "p7d-markdown-it-p-captions": "^0.21.0"
   }
 }

package/src/token-compat.js

@@ -3,18 +3,60 @@ import {
   REG_ATTRS,
   isJapaneseChar,
   hasCjkBreaksRule,
+  isCjkBreaksRuleName,
+  deriveModeInfo,
+  MODE_FLAG_COMPATIBLE,
   getRuntimeOpt,
   moveRuleAfter
 } from './token-utils.js'
 
+const isAsciiWordCode = (code) => {
+  return (code >= 0x30 && code <= 0x39) ||
+    (code >= 0x41 && code <= 0x5A) ||
+    (code >= 0x61 && code <= 0x7A)
+}
+
+const trimTrailingSpaceTab = (text) => {
+  if (!text) return text
+  let end = text.length
+  while (end > 0) {
+    const code = text.charCodeAt(end - 1)
+    if (code !== 0x20 && code !== 0x09) break
+    end--
+  }
+  return end === text.length ? text : text.slice(0, end)
+}
+
 const registerTokenCompat = (md, baseOpt) => {
-  const hasTextJoinRule = Array.isArray(md.core?.ruler?.__rules__)
-    ? md.core.ruler.__rules__.some((rule) => rule && rule.name === 'text_join')
-    : false
+  const baseModeFlags = typeof baseOpt.__strongJaModeFlags === 'number'
+    ? baseOpt.__strongJaModeFlags
+    : deriveModeInfo(baseOpt).__strongJaModeFlags
+  const baseCompatible = (baseModeFlags & MODE_FLAG_COMPATIBLE) !== 0
+  const isCompatibleMode = (state) => {
+    const override = state && state.env && state.env.__strongJaTokenOpt
+    if (!override) return baseCompatible
+    const opt = getRuntimeOpt(state, baseOpt)
+    return (opt.__strongJaModeFlags & MODE_FLAG_COMPATIBLE) !== 0
+  }
+
+  let hasTextJoinRule = false
+  const coreRules = md.core && md.core.ruler && Array.isArray(md.core.ruler.__rules__)
+    ? md.core.ruler.__rules__
+    : null
+  if (coreRules) {
+    for (let i = 0; i < coreRules.length; i++) {
+      const rule = coreRules[i]
+      if (rule && rule.name === 'text_join') {
+        hasTextJoinRule = true
+        break
+      }
+    }
+  }
 
   if (!md.__strongJaTokenTrimTrailingRegistered) {
     md.__strongJaTokenTrimTrailingRegistered = true
     const trimInlineTrailingSpaces = (state) => {
+      if (isCompatibleMode(state)) return
       if (!state || !state.tokens) return
       for (let i = 0; i < state.tokens.length; i++) {
         const token = state.tokens[i]
@@ -26,7 +68,9 @@ const registerTokenCompat = (md, baseOpt) => {
         if (idx < 0) continue
         const tail = token.children[idx]
         if (!tail || tail.type !== 'text' || !tail.content) continue
-        const trimmed = tail.content.replace(/[ \t]+$/, '')
+        const lastCode = tail.content.charCodeAt(tail.content.length - 1)
+        if (lastCode !== 0x20 && lastCode !== 0x09) continue
+        const trimmed = trimTrailingSpaceTab(tail.content)
         if (trimmed !== tail.content) {
           tail.content = trimmed
         }
@@ -42,6 +86,7 @@ const registerTokenCompat = (md, baseOpt) => {
   if (!md.__strongJaTokenSoftbreakSpacingRegistered) {
     md.__strongJaTokenSoftbreakSpacingRegistered = true
     const normalizeSoftbreakSpacing = (state) => {
+      if (isCompatibleMode(state)) return
       if (!state) return
       if (baseOpt.hasCjkBreaks !== true && state.md) {
         baseOpt.hasCjkBreaks = hasCjkBreaksRule(state.md)
@@ -51,29 +96,38 @@ const registerTokenCompat = (md, baseOpt) => {
       for (let i = 0; i < state.tokens.length; i++) {
         const token = state.tokens[i]
         if (!token || token.type !== 'inline' || !token.children || token.children.length === 0) continue
+        const children = token.children
         let hasEmphasis = false
-        for (let j = 0; j < token.children.length; j++) {
-          const child = token.children[j]
+        let hasBreakCandidate = false
+        for (let j = 0; j < children.length; j++) {
+          const child = children[j]
           if (!child) continue
           if (child.type === 'strong_open' || child.type === 'strong_close' || child.type === 'em_open' || child.type === 'em_close') {
             hasEmphasis = true
-            break
           }
+          if (!hasBreakCandidate &&
+              (child.type === 'softbreak' ||
+                (child.type === 'text' && child.content && child.content.indexOf('\n') !== -1))) {
+            hasBreakCandidate = true
+          }
+          if (hasEmphasis && hasBreakCandidate) break
         }
-        for (let j = 0; j < token.children.length; j++) {
-          const child = token.children[j]
+        if (!hasEmphasis) continue
+        if (!hasBreakCandidate) continue
+        for (let j = 0; j < children.length; j++) {
+          const child = children[j]
           if (!child) continue
           if (child.type === 'softbreak') {
-            if (!hasEmphasis) continue
-            const prevToken = token.children[j - 1]
-            const nextToken = token.children[j + 1]
+            const prevToken = children[j - 1]
+            const nextToken = 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 &&
+              isJapaneseChar(prevCharCode) && !isJapaneseChar(nextCharCode)
             if (!shouldReplace) continue
             child.type = 'text'
             child.tag = ''
@@ -83,16 +137,16 @@ const registerTokenCompat = (md, baseOpt) => {
             continue
           }
           if (child.type !== 'text' || !child.content) continue
-          if (!hasEmphasis) continue
           if (child.content.indexOf('\n') === -1) continue
           let normalized = ''
           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 &&
+                isJapaneseChar(prevCharCode) && !isJapaneseChar(nextCharCode)
               if (shouldReplace) {
                 normalized += ' '
                 continue
@@ -114,9 +168,13 @@ const registerTokenCompat = (md, baseOpt) => {
   }
 
   const restoreSoftbreaksAfterCjk = (state) => {
+    if (isCompatibleMode(state)) return
     if (!state) return
-    const opt = getRuntimeOpt(state, baseOpt)
-    if (opt.mditAttrs !== false) return
+    const overrideOpt = state.env && state.env.__strongJaTokenOpt
+    if (overrideOpt) {
+      const opt = getRuntimeOpt(state, baseOpt)
+      if (opt.mditAttrs !== false) return
+    }
     if (!state.md || state.md.__strongJaRestoreSoftbreaksForAttrs !== true) return
     if (baseOpt.hasCjkBreaks !== true && state.md) {
       baseOpt.hasCjkBreaks = hasCjkBreaksRule(state.md)
@@ -127,27 +185,26 @@ 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 = ''
       }
     }
   }
@@ -160,16 +217,17 @@ const registerTokenCompat = (md, baseOpt) => {
     if (added !== false) {
       md.__strongJaTokenRestoreRegistered = true
       md.__strongJaRestoreSoftbreaksForAttrs = baseOpt.mditAttrs === false
-      if (baseOpt.hasCjkBreaks) {
-        moveRuleAfter(md.core.ruler, 'strong_ja_restore_softbreaks', 'cjk_breaks')
-      }
       if (baseOpt.patchCorePush !== false && !md.__strongJaTokenPatchCorePush) {
         md.__strongJaTokenPatchCorePush = true
         const originalPush = md.core.ruler.push.bind(md.core.ruler)
         md.core.ruler.push = (name, fn, options) => {
           const res = originalPush(name, fn, options)
-          if (name && name.indexOf && name.indexOf('cjk_breaks') !== -1) {
+          if (isCjkBreaksRuleName(name)) {
             baseOpt.hasCjkBreaks = true
+            md.__strongJaHasCjkBreaks = true
+            if (Array.isArray(md.core.ruler.__rules__)) {
+              md.__strongJaCjkBreaksRuleCount = md.core.ruler.__rules__.length
+            }
             moveRuleAfter(md.core.ruler, 'strong_ja_restore_softbreaks', name)
           }
           return res
@@ -185,9 +243,13 @@ const registerTokenCompat = (md, baseOpt) => {
   if (baseOpt.mditAttrs !== false && !md.__strongJaTokenPreAttrsRegistered) {
     md.__strongJaTokenPreAttrsRegistered = true
     md.core.ruler.before('linkify', 'strong_ja_token_pre_attrs', (state) => {
+      if (isCompatibleMode(state)) return
       if (!state || !state.tokens) return
-      const opt = getRuntimeOpt(state, baseOpt)
-      if (opt.mditAttrs === false) return
+      const overrideOpt = state.env && state.env.__strongJaTokenOpt
+      if (overrideOpt) {
+        const opt = getRuntimeOpt(state, baseOpt)
+        if (opt.mditAttrs === false) return
+      }
       for (let i = 0; i < state.tokens.length; i++) {
         const token = state.tokens[i]
         if (!token || token.type !== 'inline' || !token.children || token.children.length === 0) continue