perf: 📜️更新版本;对于特殊内容文档兼容
This commit is contained in:
parent
2b3e330841
commit
200f415ac6
Binary file not shown.
@ -427,7 +427,7 @@ namespace AIProofread
|
||||
{
|
||||
Logger.Log(ex);
|
||||
data["code"] = 5;
|
||||
data["message"] = "文档格式有误，请另存文档后再进行校对";
|
||||
data["message"] = "文档格式有误或内容异常，请另存文档后再进行校对";
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
|
||||
@ -36,7 +36,7 @@ namespace AIProofread
|
||||
public class Config
|
||||
{
|
||||
public static readonly string APP_NAME = "AI校对王";
|
||||
public static readonly string APP_VERSION = "2.2.2";
|
||||
public static readonly string APP_VERSION = "2.2.3";
|
||||
public static bool IS_WPS = false;
|
||||
public static bool UpgradeForcedNotice = false;
|
||||
public static readonly string APP_BASE_DIR = AppDomain.CurrentDomain.BaseDirectory;
|
||||
|
||||
@ -7,10 +7,10 @@ using System.Security;
|
||||
// 控制。更改这些特性值可修改
|
||||
// 与程序集关联的信息。
|
||||
[assembly: AssemblyTitle("AI校对王")]
|
||||
[assembly: AssemblyDescription("AI校对王 2.2.1")]
|
||||
[assembly: AssemblyDescription("AI校对王 2.2.3")]
|
||||
[assembly: AssemblyConfiguration("")]
|
||||
[assembly: AssemblyCompany("果麦文化传媒股份有限公司")]
|
||||
[assembly: AssemblyProduct("AI校对王 2.2.1")]
|
||||
[assembly: AssemblyProduct("AI校对王 2.2.3")]
|
||||
[assembly: AssemblyCopyright("Copyright © 果麦文化传媒股份有限公司 2025")]
|
||||
[assembly: AssemblyTrademark("")]
|
||||
[assembly: AssemblyCulture("")]
|
||||
@ -34,5 +34,5 @@ using System.Security;
|
||||
// 方法是按如下所示使用“*”: :
|
||||
// [assembly: AssemblyVersion("1.0.*")]
|
||||
[assembly: AssemblyVersion("2.0")]
|
||||
[assembly: AssemblyFileVersion("2.2.1.0")]
|
||||
[assembly: AssemblyFileVersion("2.2.3.0")]
|
||||
|
||||
|
||||
@ -8,6 +8,7 @@ using System;
|
||||
using System.Collections.Generic;
|
||||
using System.Diagnostics;
|
||||
using System.IO;
|
||||
using System.IO.Compression;
|
||||
using System.Runtime.InteropServices;
|
||||
using System.Security.Cryptography;
|
||||
|
||||
@ -41,22 +42,34 @@ namespace AIProofread
|
||||
List<DocumentText> list = new List<DocumentText>();
|
||||
|
||||
//DocumentReader.ReadByVSTO(doc, Globals.ThisAddIn.Application, list);
|
||||
using (FileStream stream = new FileStream(docPath, FileMode.Open, FileAccess.Read, FileShare.ReadWrite))
|
||||
try
|
||||
{
|
||||
ReadTextByNPOI(stream, list);
|
||||
//try
|
||||
//{
|
||||
|
||||
//}
|
||||
//catch (POIXMLException npoiError)
|
||||
//{
|
||||
// Logger.Log("GetAllText Error", npoiError);
|
||||
// // Logger.Log("GetAllText", e);
|
||||
// // return GetAllTextByVSTO(doc);
|
||||
// // 读取文档
|
||||
// DocumentReader.ReadByVSTO(doc, Globals.ThisAddIn.Application, list);
|
||||
//}
|
||||
ReadTextByNPOI(docPath, list);
|
||||
}
|
||||
catch (POIXMLException ex)
|
||||
{
|
||||
// 编号有误,移除编号再读取
|
||||
if (ex.StackTrace.Contains("NPOI.XWPF.UserModel.XWPFNumbering"))
|
||||
{
|
||||
RemoveNumbersReadTextByNPOI(docPath, list);
|
||||
}
|
||||
}
|
||||
//using (FileStream stream = new FileStream(docPath, FileMode.Open, FileAccess.Read, FileShare.ReadWrite))
|
||||
//{
|
||||
|
||||
// //try
|
||||
// //{
|
||||
|
||||
// //}
|
||||
// //catch (POIXMLException npoiError)
|
||||
// //{
|
||||
// // Logger.Log("GetAllText Error", npoiError);
|
||||
// // // Logger.Log("GetAllText", e);
|
||||
// // // return GetAllTextByVSTO(doc);
|
||||
// // // 读取文档
|
||||
// // DocumentReader.ReadByVSTO(doc, Globals.ThisAddIn.Application, list);
|
||||
// //}
|
||||
//}
|
||||
var map = new Dictionary<string, object>
|
||||
{
|
||||
{ "list", list },
|
||||
@ -67,55 +80,73 @@ namespace AIProofread
|
||||
return map;
|
||||
}
|
||||
|
||||
private static void ReadTextByNPOI(FileStream stream, List<DocumentText> list)
|
||||
private static void RemoveNumbersReadTextByNPOI(string filePath, List<DocumentText> list)
|
||||
{
|
||||
XWPFDocument ndoc = new XWPFDocument(stream);
|
||||
var paragraphs = ndoc.Paragraphs;
|
||||
int paragraphNumber = 1;
|
||||
foreach (var bodyElement in ndoc.BodyElements)
|
||||
list.Clear();
|
||||
var fs = File.OpenWrite(filePath);
|
||||
// 打开Zip文件,删除 numbering.xml
|
||||
using (ZipArchive archive = new ZipArchive(fs, ZipArchiveMode.Update))
|
||||
{
|
||||
// normal paragraph
|
||||
if (bodyElement is XWPFParagraph p)
|
||||
var numberingEntry = archive.GetEntry("word/numbering.xml");
|
||||
numberingEntry?.Delete(); // 删除 numbering.xml
|
||||
}
|
||||
fs.Close();
|
||||
ReadTextByNPOI(filePath, list);
|
||||
}
|
||||
|
||||
private static void ReadTextByNPOI(string filePath, List<DocumentText> list)
|
||||
{
|
||||
//, FileMode.Open, FileAccess.Read, FileShare.ReadWrite
|
||||
using (var stream = File.OpenRead(filePath))
|
||||
{
|
||||
XWPFDocument ndoc = new XWPFDocument(stream);
|
||||
var paragraphs = ndoc.Paragraphs;
|
||||
int paragraphNumber = 1;
|
||||
foreach (var bodyElement in ndoc.BodyElements)
|
||||
{
|
||||
// 处理普通段落
|
||||
var text = p.ParagraphText.Replace("\u0002", "");
|
||||
if(text.Trim().Length > 0)
|
||||
// normal paragraph
|
||||
if (bodyElement is XWPFParagraph p)
|
||||
{
|
||||
list.Add(new DocumentText(text, paragraphNumber));
|
||||
}
|
||||
paragraphNumber++;
|
||||
}
|
||||
// table -- vsto对于每个单元格的分段也会有
|
||||
else if (bodyElement is XWPFTable table)
|
||||
{
|
||||
foreach (var row in table.Rows)
|
||||
{
|
||||
foreach (var cell in row.GetTableCells())
|
||||
// 处理普通段落
|
||||
var text = p.ParagraphText.Replace("\u0002", "");
|
||||
if (text.Trim().Length > 0)
|
||||
{
|
||||
foreach (var pc in cell.Paragraphs)
|
||||
{
|
||||
list.Add(new DocumentText(pc.ParagraphText.Replace("\u0002", ""), paragraphNumber));
|
||||
paragraphNumber++;
|
||||
}
|
||||
list.Add(new DocumentText(text, paragraphNumber));
|
||||
}
|
||||
//list.Add(string.Empty);
|
||||
paragraphNumber++;
|
||||
}
|
||||
}
|
||||
// 目录处理
|
||||
else if (bodyElement is XWPFSDT sdt)
|
||||
{
|
||||
string tocText = sdt.Content.Text;
|
||||
// table -- vsto对于每个单元格的分段也会有
|
||||
else if (bodyElement is XWPFTable table)
|
||||
{
|
||||
foreach (var row in table.Rows)
|
||||
{
|
||||
foreach (var cell in row.GetTableCells())
|
||||
{
|
||||
foreach (var pc in cell.Paragraphs)
|
||||
{
|
||||
list.Add(new DocumentText(pc.ParagraphText.Replace("\u0002", ""), paragraphNumber));
|
||||
paragraphNumber++;
|
||||
}
|
||||
}
|
||||
//list.Add(string.Empty);
|
||||
paragraphNumber++;
|
||||
}
|
||||
}
|
||||
// 目录处理
|
||||
else if (bodyElement is XWPFSDT sdt)
|
||||
{
|
||||
string tocText = sdt.Content.Text;
|
||||
|
||||
// 如果需要，可以进一步解析目录项// 例如，按换行符拆分目录内容
|
||||
var tocEntries = tocText.Split(new string[] { "\n", "\r", "\r\n", "\f" }, StringSplitOptions.None);
|
||||
paragraphNumber+= tocEntries.Length;
|
||||
// 暂时跳过目录
|
||||
//foreach (string entry in tocEntries)
|
||||
//{
|
||||
// list.Add(new DocumentText(entry.Replace("\u0002", ""), paragraphNumber));
|
||||
// paragraphNumber++;
|
||||
//}
|
||||
// 如果需要，可以进一步解析目录项// 例如，按换行符拆分目录内容
|
||||
var tocEntries = tocText.Split(new string[] { "\n", "\r", "\r\n", "\f" }, StringSplitOptions.None);
|
||||
paragraphNumber += tocEntries.Length;
|
||||
// 暂时跳过目录
|
||||
//foreach (string entry in tocEntries)
|
||||
//{
|
||||
// list.Add(new DocumentText(entry.Replace("\u0002", ""), paragraphNumber));
|
||||
// paragraphNumber++;
|
||||
//}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user