public ActionResult read(string id)
{
DocumentEntity doc = _repository.Single <DocumentEntity>(id);
var fields = typeof(ConvertComponentType).GetFields(BindingFlags.Static | BindingFlags.Public);
var componentName = ConfigurationManager.AppSettings["Component"];
ConvertComponentType selectenum = (ConvertComponentType)Enum.Parse(typeof(ConvertComponentType), componentName, false);
ConvertDocument convertdoc = new ConvertDocument(doc, selectenum);
///未考虑到的情况： 如果文档已经解析完毕，是否需要重新解析
///留下与后续数据存放的逻辑一同实现
///update 2014-12-11已完成 逻辑在ProcessDocument中实现
JsonDocEntity parseEntity = convertdoc.ProcessDocument();
//若解析文档不成功，则直接返回
if (parseEntity != null)
{
//若文档已经存储过，则跳过存储逻辑
if (!convertdoc._docEntity.isStore)
{
convertdoc._docEntity.isStore = true;
_repository.Update <DocumentEntity>(convertdoc._docEntity);
}
return(Json(parseEntity, JsonRequestBehavior.AllowGet));
}
return(null);
}
public override JsonDocEntity ParseHtmlToEntity(DocumentEntity _docEntity)
{
if (_docEntity.isConvert && !_docEntity.isParse)
{
var htmldata = _docEntity.HtmlData.HtmlContent[0];
///清空当前对象存储HTML解析格式的属性
///如果已经解析过的文档就不需要重复处理了
///此动作后续需要配合存储一起重构
if (String.IsNullOrEmpty(_docEntity.HtmlData.StyleUrl))
{
var style = STYLE_REGEX.Match(htmldata).Groups["style"].Value;
FileUtils.WriteStyleFile(style, Path.Combine(_docEntity.ResourcesPath, "wpsStyle.css"));
_docEntity.HtmlData.StyleUrl = _docEntity.VirtualResourcesPath + "/" + "wpsStyle.css";
}
_docEntity.HtmlData.ParseContentList = new List <HtmlParseData>();
MatchCollection divmatches = DIV_REGEX.Matches(htmldata);
var count = 1;
foreach (Match divmatcher in divmatches)
{
HtmlParseData divcontent = new HtmlParseData();
divcontent.pagecount = count;
var div = divmatcher.Groups["div"].Value;
var imagematchers = DIV_IMAGE_REGEX.Matches(div);
HashSet <String> hs = new HashSet <string>();
foreach (Match iamgematcher in imagematchers)
{
var src = iamgematcher.Groups["src"].Value;
hs.Add(src);
}
foreach (var item in hs)
{
div = div.Replace(item, _docEntity.VirtualResourcesPath + "/" +
_docEntity.ImageFolder + "/" + Path.GetFileName(item));
}
divcontent.content = div;
_docEntity.HtmlData.ParseContentList.Add(divcontent);
count++;
}
_docEntity.ConvertCompleteTime = DateTime.Now;
_docEntity.isParse = true;
}
return(JsonDocEntity.Convert(_docEntity));
}
public override JsonDocEntity ParseHtmlToEntity(Common.Entities.DocumentEntity _docEntity)
{
///清空当前对象存储HTML解析格式的属性
///如果已经解析过的文档就不需要重复处理了
///此动作后续需要配合存储一起重构
//_docEntity.HtmlData.ParseContentList = new List<HtmlParseData>();
if (!_docEntity.isParse)
{
foreach (var htmldata in _docEntity.HtmlData.HtmlContent)
{
///获取当前工作表的表名
var worksheetname = TITLE_REGEX.Match(htmldata).Groups["name"].Value;
MatchCollection tablematches = TABLE_REGEX.Matches(htmldata);
if (String.IsNullOrEmpty(_docEntity.HtmlData.StyleUrl))
{
var style = STYLE_REGEX.Match(htmldata).Groups["style"].Value;
FileUtils.WriteStyleFile(style, Path.Combine(_docEntity.ResourcesPath, "etStyle.css"));
_docEntity.HtmlData.StyleUrl = _docEntity.VirtualResourcesPath + "/" + "etStyle.css";
}
var count = 1;
foreach (Match tablematcher in tablematches)
{
HtmlParseData divcontent = new HtmlParseData();
divcontent.pagecount = count;
divcontent.title = worksheetname;
var table = tablematcher.Groups["table"].Value;
var imagematchers = DIV_IMAGE_REGEX.Matches(table);
HashSet <String> hs = new HashSet <string>();
foreach (Match iamgematcher in imagematchers)
{
var src = iamgematcher.Groups["src"].Value;
hs.Add(src);
}
foreach (var item in hs)
{
table = table.Replace(item, _docEntity.VirtualResourcesPath + "/" +
_docEntity.ImageFolder + "/" + Path.GetFileName(item));
}
divcontent.content = table;
_docEntity.HtmlData.ParseContentList.Add(divcontent);
count++;
}
}
_docEntity.isParse = true;
_docEntity.ConvertCompleteTime = DateTime.Now;
}
return(JsonDocEntity.Convert(_docEntity));
}
public override JsonDocEntity ParseHtmlToEntity(DocumentEntity _docEntity)
{
if (!_docEntity.isParse)
{
var VirtualResourcesPath = _docEntity.VirtualResourcesPath;
for (int count = 1; count < _docEntity.HtmlData.PageNumber + 1; count++)
{
HtmlParseData divcontent = new HtmlParseData();
divcontent.pagecount = count;
divcontent.thumbUrl = VirtualResourcesPath + "/Small/" + String.Format("Thumbnail{0}.jpg", count);
divcontent.url = VirtualResourcesPath + "/Big/" + String.Format("Thumbnail{0}.jpg", count);
_docEntity.HtmlData.ParseContentList.Add(divcontent);
}
_docEntity.ConvertCompleteTime = DateTime.Now;
_docEntity.isParse = true;
}
return(JsonDocEntity.Convert(_docEntity));
}
public override JsonDocEntity ParseHtmlToEntity(Common.Entities.DocumentEntity _docEntity)
{
if (!_docEntity.isParse)
{
//Excel的文件读取因为涉及到frame里的表关系，所以暂时放置在Parse的逻辑中完成：
var outputpath = Path.Combine(_docEntity.ResourcesPath, "ConvertFolder.files");
string[] Files = Directory.GetFiles(outputpath);
Dictionary <string, string> ParseData = new Dictionary <string, string>();
string tabstrip = "";
foreach (var filename in Files)
{
if (filename.EndsWith("tabstrip.htm"))
{
tabstrip = FileUtils.ReadFile(filename);
}
if (filename.EndsWith("stylesheet.css"))
{
FileUtils.WriteStyleFile(FileUtils.ReadFile(filename), Path.Combine(_docEntity.ResourcesPath, "etStyle.css"));
}
}
MatchCollection mapping = Structure_Mapping.Matches(tabstrip);
foreach (Match match in mapping)
{
var path = Path.Combine(outputpath, match.Groups["src"].Value);
var content = Util.FileUtils.ReadFile(path);
var name = match.Groups["Name"].Value;
ParseData.Add(name, content);
_docEntity.HtmlData.HtmlContent.Add(content);
}
foreach (var parsedataitem in ParseData)
{
///获取当前工作表的表名
var worksheetname = parsedataitem.Key; //TITLE_REGEX.Match(parsedataitem.Value).Groups["name"].Value;
MatchCollection tablematches = TABLE_REGEX.Matches(parsedataitem.Value);
if (String.IsNullOrEmpty(_docEntity.HtmlData.StyleUrl))
{
_docEntity.HtmlData.StyleUrl = _docEntity.VirtualResourcesPath + "/" + "etStyle.css";
}
var count = 1;
foreach (Match tablematcher in tablematches)
{
HtmlParseData divcontent = new HtmlParseData();
divcontent.pagecount = count;
divcontent.title = worksheetname;
var table = tablematcher.Groups["table"].Value;
var imagematchers = DIV_IMAGE_REGEX.Matches(table);
HashSet <String> hs = new HashSet <string>();
foreach (Match iamgematcher in imagematchers)
{
var src = iamgematcher.Groups["href"].Value;
hs.Add(src);
}
foreach (var item in hs)
{
table = table.Replace(item, _docEntity.VirtualResourcesPath + "/" +
_docEntity.ImageFolder + "/" + Path.GetFileName(item));
}
divcontent.content = table;
_docEntity.HtmlData.ParseContentList.Add(divcontent);
count++;
}
}
_docEntity.isParse = true;
_docEntity.ConvertCompleteTime = DateTime.Now;
}
return(JsonDocEntity.Convert(_docEntity));
}
