w-docx-split 1.0.0

package/docs/styles/prettify.css

@@ -0,0 +1,80 @@
+.pln {
+  color: #ddd;
+}
+
+/* string content */
+.str {
+  color: #61ce3c;
+}
+
+/* a keyword */
+.kwd {
+  color: #fbde2d;
+}
+
+/* a comment */
+.com {
+  color: #aeaeae;
+}
+
+/* a type name */
+.typ {
+  color: #8da6ce;
+}
+
+/* a literal value */
+.lit {
+  color: #fbde2d;
+}
+
+/* punctuation */
+.pun {
+  color: #ddd;
+}
+
+/* lisp open bracket */
+.opn {
+  color: #000000;
+}
+
+/* lisp close bracket */
+.clo {
+  color: #000000;
+}
+
+/* a markup tag name */
+.tag {
+  color: #8da6ce;
+}
+
+/* a markup attribute name */
+.atn {
+  color: #fbde2d;
+}
+
+/* a markup attribute value */
+.atv {
+  color: #ddd;
+}
+
+/* a declaration */
+.dec {
+  color: #EF5050;
+}
+
+/* a variable name */
+.var {
+  color: #c82829;
+}
+
+/* a function name */
+.fun {
+  color: #4271ae;
+}
+
+/* Specify class=linenums on a pre to get line numbering */
+ol.linenums {
+  margin-top: 0;
+  margin-bottom: 0;
+  padding-bottom: 2px;
+}

package/g.mjs

@@ -0,0 +1,29 @@
+import w from 'wsemi'
+import WDocxSplit from './src/WDocxSplit.mjs'
+//import WDocxSplit from 'w-docx-split/src/WDocxSplit.mjs'
+//import WDocxSplit from 'w-docx-split'
+
+
+async function test() {
+
+    let fpIn = `./test/docin.docx`
+    let strSep = '[systag:sepline]'
+    let fdOut = `./test/out`
+    let opt = {
+        padZero: 3,
+    }
+
+    let r = await WDocxSplit(fpIn, strSep, fdOut, opt)
+    console.log(r)
+    // => ok
+
+    w.fsDeleteFolder(fdOut)
+
+}
+test()
+    .catch((err) => {
+        console.log('catch', err)
+    })
+
+
+//node g.mjs

package/package.json

@@ -0,0 +1,32 @@
+{
+  "name": "w-docx-split",
+  "version": "1.0.0",
+  "main": "dist/w-docx-split.umd.js",
+  "dependencies": {
+    "lodash-es": "^4.17.22",
+    "wsemi": "^1.8.38"
+  },
+  "devDependencies": {
+    "w-package-tools": "^1.1.2"
+  },
+  "scripts": {
+    "postinstall": "node scripts/install.mjs",
+    "test": "mocha --parallel --timeout 60000",
+    "deploy": "gh-pages -d docs"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/yuda-lyu/w-docx-split.git"
+  },
+  "keywords": [
+    "package",
+    "tool",
+    "win32com",
+    "html",
+    "docx",
+    "windows",
+    "nodejs"
+  ],
+  "author": "yuda-lyu(semisphere)",
+  "license": "MIT"
+}

package/script.txt

@@ -0,0 +1,17 @@
+#node toolg/addVersion.mjs
+node toolg/modifyReadme.mjs
+
+node toolg/cleanFolder.mjs
+./node_modules/.bin/jsdoc -c .jsdoc
+
+node toolg/gDistRollup.mjs
+
+git add .  -A
+git commit -m 'modify: '
+git push origin master:master
+
+npm run deploy
+
+#npm test
+
+#npm publish

package/scripts/install.mjs

@@ -0,0 +1,30 @@
+import path from 'path'
+import { fileURLToPath } from 'url'
+import downloadFiles from '../src/downloadFiles.mjs'
+
+
+async function init() {
+
+    //check, 被安裝條件才執行
+    let __dirname = path.dirname(fileURLToPath(import.meta.url))
+    if (!__dirname.includes('node_modules')) {
+        return //非位於node_modules, 代表套件本身
+    }
+
+    //fdSrv
+    let fdSrv = path.resolve()
+
+    //fdBase,
+    let fdBase = `${fdSrv}/src/` //npm i後觸發安裝時, 工作路徑是位於套件內
+    // console.log('fdBase', fdBase)
+
+    //downloadFiles
+    await downloadFiles(fdBase)
+
+}
+init()
+    .catch((err) => {
+        console.log(err)
+    })
+
+//node scripts/install.mjs

package/src/WDocxSplit.mjs

@@ -0,0 +1,127 @@
+import path from 'path'
+import process from 'process'
+import get from 'lodash-es/get.js'
+import isestr from 'wsemi/src/isestr.mjs'
+import isp0int from 'wsemi/src/isp0int.mjs'
+import str2b64 from 'wsemi/src/str2b64.mjs'
+import execProcess from 'wsemi/src/execProcess.mjs'
+import fsIsFile from 'wsemi/src/fsIsFile.mjs'
+import fsIsFolder from 'wsemi/src/fsIsFolder.mjs'
+import fsCreateFolder from 'wsemi/src/fsCreateFolder.mjs'
+
+
+let fdSrv = path.resolve()
+
+
+function isWindows() {
+    return process.platform === 'win32'
+}
+
+
+/**
+ * 依照指定字串分割Docx檔
+ *
+ * @param {String} fpIn 輸入來源Html檔位置字串
+ * @param {String} strSep 輸入內文會提供之分割字串
+ * @param {String} fdOut 輸入轉出Docx檔位置字串
+ * @param {Object} [opt={}] 輸入設定物件，預設{}
+ * @param {Integer} [opt.padZero=0] 輸入是否補0位數整數，例如padZero=3時檔名會變成001.docx，預設0
+ * @returns {Promise} 回傳Promise，resolve回傳成功訊息，reject回傳錯誤訊息
+ * @example
+ *
+
+ *
+ */
+async function WDocxSplit(fpIn, strSep, fdOut, opt = {}) {
+    let errTemp = null
+
+    //isWindows
+    if (!isWindows()) {
+        return Promise.reject('operating system is not windows')
+    }
+
+    //check
+    if (!fsIsFile(fpIn)) {
+        return Promise.reject(`fpIn[${fpIn}] does not exist`)
+    }
+
+    //check
+    if (!isestr(strSep)) {
+        return Promise.reject(`strSep[${strSep}] is not an effective string`)
+    }
+
+    //check
+    if (!fsIsFolder(fdOut)) {
+        fsCreateFolder(fdOut)
+    }
+
+    //padZero
+    let padZero = get(opt, 'padZero')
+    if (!isp0int(padZero)) {
+        padZero = 0
+    }
+
+    //轉絕對路徑
+    fpIn = path.resolve(fpIn)
+    fdOut = path.resolve(fdOut)
+
+    //fnExe
+    let fnExe = `splitDocx.exe`
+
+    //fdExe
+    let fdExe = ''
+    if (true) {
+        let fdExeSrc = `${fdSrv}/src/`
+        let fdExeNM = `${fdSrv}/node_modules/w-docx-split/src/`
+        if (fsIsFile(`${fdExeSrc}${fnExe}`)) {
+            fdExe = fdExeSrc
+        }
+        else if (fsIsFile(`${fdExeNM}${fnExe}`)) {
+            fdExe = fdExeNM
+        }
+        else {
+            return Promise.reject('can not find folder for html2docx')
+        }
+    }
+    // console.log('fdExe', fdExe)
+
+    //prog
+    let prog = `${fdExe}${fnExe}`
+    // console.log('prog', prog)
+
+    //inp
+    let inp = {
+        fpIn,
+        strSep,
+        fdOut,
+        padZero,
+    }
+    // console.log('inp', inp)
+
+    //input to b64
+    let cInput = JSON.stringify(inp)
+    let b64Input = str2b64(cInput)
+    // console.log('b64Input', b64Input)
+
+    //execProcess
+    await execProcess(prog, b64Input)
+        .catch((err) => {
+            console.log('execProcess catch', err)
+            errTemp = err.toString()
+        })
+
+    //check
+    if (errTemp) {
+        return Promise.reject(errTemp)
+    }
+
+    // //check
+    // if (!isestr(output)) {
+    //     return Promise.reject(`output[${cstr(output)}] is not an effective string`)
+    // }
+
+    return 'ok'
+}
+
+
+export default WDocxSplit

package/src/downloadFiles.mjs

@@ -0,0 +1,23 @@
+import fsDownloadFile from 'wsemi/src/fsDownloadFile.mjs'
+
+
+async function downloadFiles(fdBase) {
+
+    //url
+    let url = `https://github.com/yuda-lyu/w-docx-split/raw/refs/heads/master/src/splitDocx.exe`
+    // console.log('url',url)
+
+    //fn
+    let fn = `splitDocx.exe`
+
+    //fp
+    let fp = `${fdBase}${fn}`
+
+    //fsDownloadFile
+    console.log(`downloading url[${url}]...`, `to fp[${fp}]`)
+    await fsDownloadFile(url, fp)
+
+}
+
+
+export default downloadFiles

package/srcPython/build.bat

@@ -0,0 +1,9 @@
+
+pyinstaller -F splitDocx.py
+pause
+
+pyinstaller build.spec
+pause
+
+pyinstaller splitDocx.py
+pause

package/srcPython/run.bat

@@ -0,0 +1,4 @@
+python splitDocx.py testb64
+pause
+
+#測試版使用

package/srcPython/splitDocx.py

@@ -0,0 +1,271 @@
+from win32com import client as wc  
+
+#使用win32com
+#win32com因更新問題會出現 ImportError: DLL load failed while importing win32api: 找不到指定的模組。
+#1. 安裝 pip install pywin32
+#2. 使用系統管理員權限開啟cmd
+#3. cd至安裝目錄 C:\ProgramData\Anaconda3\Scripts
+#4. 用python安裝腳本 python pywin32_postinstall.py -install
+
+#編譯
+#1. 安裝編譯套件 pip install pyinstaller
+#2. 編譯 pyinstaller -F splitDocx.py
+
+#win32com教學
+#https://zhuanlan.zhihu.com/p/67543981
+
+
+def getError():
+    import sys
+
+    #exc_info
+    type, message, traceback = sys.exc_info()
+
+    #es
+    es=[]
+    while traceback:
+        e={
+            'name':traceback.tb_frame.f_code.co_name,
+            'filename':traceback.tb_frame.f_code.co_filename,
+        }
+        es.append(e)
+        traceback = traceback.tb_next
+
+    #err
+    err={
+        'type':type,
+        'message':message,
+        'traceback':es,
+    }
+
+    return err
+
+
+def j2o(v):
+    #json轉物件
+    import json
+    return json.loads(v)
+
+
+def o2j(v):
+    #物件轉json
+    import json
+    return json.dumps(v, ensure_ascii=False)
+
+
+def str2b64(v):
+    #字串轉base64字串
+    import base64
+    v=base64.b64encode(v.encode('utf-8'))
+    return str(v,'utf-8')
+    
+
+def b642str(v):
+    #base64字串轉字串
+    import base64
+    return base64.b64decode(v)
+
+
+def readText(fn):
+    #讀取檔案fn內文字
+    import codecs
+    with codecs.open(fn,'r',encoding='utf8') as f:
+        return f.read()
+
+    
+def writeText(fn,str):
+    #寫出文字str至檔案fn
+    import codecs
+    with codecs.open(fn,'w',encoding='utf8') as f:
+        f.write(str)
+
+
+def splitDocx(fpIn, strSep, fdOut, opt):
+
+    #Dispatch
+    app = wc.Dispatch('Word.Application')
+
+    #正式版須隱藏
+    app.Visible = False  
+
+    #不詢問使用者
+    app.DisplayAlerts = False 
+
+    docIn = None
+    try:
+
+        # Open
+        docIn = app.Documents.Open(fpIn)
+
+        # 逐段落掃描
+        # Word 的 Paragraphs 索引是 1-based
+        # 先掃一次切成多組 paragraph index 區間
+        groups = []
+        cur = []
+        i = 0
+        for p in docIn.Paragraphs:
+            i += 1
+            t = p.Range.Text or ""
+
+            # 判斷是否為分隔段
+            is_sep = (strSep in t)
+
+            if is_sep:
+                if len(cur) > 0:
+                    groups.append(cur)
+                cur = []
+            else:
+                cur.append(i)
+
+        if len(cur) > 0:
+            groups.append(cur)
+
+        # 沒任何內容也要合理處理
+        # groups 可能為 []，代表整份文件都是分隔符或空
+        total = len(groups)
+
+        # 逐組輸出
+        padZero = opt.get('padZero', None)
+
+        for idx, paraIdxList in enumerate(groups, start=1):
+
+            # 檔名：1.docx ~ n.docx
+            if isinstance(padZero, int) and padZero > 0:
+                fn = str(idx).zfill(padZero) + '.docx'
+            else:
+                fn = str(idx) + '.docx'
+
+            # 若 fdOut 結尾已有\會變成\\, 得使用rstrip處理
+            fpOut = fdOut.rstrip('\\/') + '\\' + fn
+
+            # Add new document
+            docOut = app.Documents.Add()
+
+            try:
+                # 逐段落拷貝格式化內容（不走剪貼簿）
+                # 用 rngOut 的結尾做 append
+                rngOut = docOut.Content
+                WdCollapseEnd = 0  # wdCollapseEnd
+                for pi in paraIdxList:
+                    rngSrc = docIn.Paragraphs(pi).Range
+                    rngOut.Collapse(WdCollapseEnd)
+
+                    # 這句是關鍵：不經剪貼簿，直接拷貝格式化文字
+                    rngOut.FormattedText = rngSrc.FormattedText
+
+                # SaveAs2
+                WdSaveFormat = 16  # wdFormatDocumentDefault=16 (.docx)
+                docOut.SaveAs2(fpOut, WdSaveFormat)
+
+            finally:
+                # Close output doc
+                try:
+                    WdDoNotSaveChanges = 0  # wdDoNotSaveChanges
+                    docOut.Close(WdDoNotSaveChanges)
+                except:
+                    pass
+
+        return {
+            'total': total,
+            'fdOut': fdOut,
+        }
+
+    finally:
+        # Close input doc & quit word
+        try:
+            if docIn is not None:
+                WdDoNotSaveChanges = 0
+                docIn.Close(WdDoNotSaveChanges)
+        except:
+            pass
+
+        try:
+            WdSaveOptions = 0  # wdDoNotSaveChanges
+            app.Quit(WdSaveOptions)
+        except:
+            pass
+
+
+def core(b64):
+    state=''
+
+    try:
+
+        #b642str
+        s=b642str(b64)
+
+        #j2o
+        o=j2o(s)
+
+        #params
+        fpIn=o['fpIn']
+        strSep=o['strSep']
+        fdOut=o['fdOut']
+
+        #opt
+        opt={}
+        opt['padZero']=o['padZero']
+
+        #splitDocx
+        splitDocx(fpIn, strSep, fdOut, opt)
+
+        state='success'
+    except:
+        err=getError()
+        state='error: '+str(err["message"])
+
+    return state
+
+
+def run():
+    import sys
+
+    #由外部程序呼叫或直接給予檔案路徑
+    state=''
+    argv=sys.argv
+    #argv=['','']
+    if len(argv)==2:
+        
+        #b64
+        b64=sys.argv[1]
+        
+        #core
+        state=core(b64)
+        
+    else:
+        #print(sys.argv)
+        state='error: invalid length of argv'
+    
+    #print & flush
+    print(state)
+    sys.stdout.flush()
+
+
+if True:
+    #正式版
+    
+    #run
+    run()
+    
+    
+if False:
+    #產生測試輸入b64
+    
+    #inp
+    inp={
+        'fpIn':'D:\\- 006 -        開源\\開源-JS-008-4-w-docx-split\\w-docx-split\\srcPython\\bbb\\docin.docx',
+        'strSep':'[systag:sepline]',
+        'fdOut':'D:\\- 006 -        開源\\開源-JS-008-4-w-docx-split\\w-docx-split\\srcPython\\bbb2',
+        'padZero': 0,
+    }
+    # print(o2j(inp))
+    
+    #str2b64
+    b64=str2b64(o2j(inp))
+    print(b64)
+
+    #core
+    state=core(b64)
+
+    print(state)
+

package/srcPython/splitDocx.spec

@@ -0,0 +1,37 @@
+# -*- mode: python ; coding: utf-8 -*-
+
+
+a = Analysis(
+    ['splitDocx.py'],
+    pathex=[],
+    binaries=[],
+    datas=[],
+    hiddenimports=[],
+    hookspath=[],
+    hooksconfig={},
+    runtime_hooks=[],
+    excludes=[],
+    noarchive=False,
+)
+pyz = PYZ(a.pure)
+
+exe = EXE(
+    pyz,
+    a.scripts,
+    a.binaries,
+    a.datas,
+    [],
+    name='splitDocx',
+    debug=False,
+    bootloader_ignore_signals=False,
+    strip=False,
+    upx=True,
+    upx_exclude=[],
+    runtime_tmpdir=None,
+    console=True,
+    disable_windowed_traceback=False,
+    argv_emulation=False,
+    target_arch=None,
+    codesign_identity=None,
+    entitlements_file=None,
+)

package/srcPython//350/252/252/346/230/216.txt

@@ -0,0 +1,24 @@
+
+0.可用pyinstaller或nuitka編譯，但nuitka編譯出檔案會小一點(4x mb)，不過卻無法執行待研究
+
+1.可先用一般編譯方式產生spec檔: pyinstaller -F splitDocx.py，就會產生splitDocx.spec
+
+2.若有需要修改spec後，編譯指令改為對spec檔編譯: pyinstaller build.spec
+
+3.使用build.bat進行編譯
+
+8.編譯完複製splitDocx.exe至bin，使用bin\run.bat執行，傳入的b64可將物件
+{
+    'fpIn':'input.html',
+    'fpOut':'output.docx'
+}
+序列化成字串再轉base64即可
+
+----------------------------------------------------------------------
+參考
+
+解决方法：pyinstaller打包缺文件
+https://www.geek-share.com/detail/2773482967.html
+
+pyinstaller spec文件
+https://pyinstaller.readthedocs.io/en/stable/spec-files.html