【问题标题】:Word XML to RTF conversionWord XML 到 RTF 的转换
【发布时间】:2010-04-10 09:49:35
【问题描述】:

我需要以编程方式将 Word-XML 文件转换为 RTF 文件。由于某些第三方库,它已成为一项要求。任何可以做到这一点的 API/库?

实际上语言不是问题,因为我只需要完成工作。但首选 Java、.NET 语言或 Python。

【问题讨论】:

    标签: java .net python xml rtf


    【解决方案1】:

    一种 Python/linux 方式:

    您需要 OpenOffice Uno Bride(在服务器上,您可以在无头模式下运行 OO)。 因此,您可以将每种 OO 可读格式转换为每种 OO 可写格式:

    http://wiki.services.openoffice.org/wiki/Framework/Article/Filter/FilterList_OOo_3_0

    运行示例代码

    /usr/lib64/openoffice.org/program/soffice.bin -accept=socket,host=localhost,port=8100\;urp -headless
    

    Python 示例:

    import uno
    from os.path import abspath, isfile, splitext
    from com.sun.star.beans import PropertyValue
    from com.sun.star.task import ErrorCodeIOException
    from com.sun.star.connection import NoConnectException
    
    FAMILY_TEXT = "Text"
    FAMILY_SPREADSHEET = "Spreadsheet"
    FAMILY_PRESENTATION = "Presentation"
    FAMILY_DRAWING = "Drawing"
    DEFAULT_OPENOFFICE_PORT = 8100
    
    FILTER_MAP = {
        "pdf": {
            FAMILY_TEXT: "writer_pdf_Export",
            FAMILY_SPREADSHEET: "calc_pdf_Export",
            FAMILY_PRESENTATION: "impress_pdf_Export",
            FAMILY_DRAWING: "draw_pdf_Export"
        },
        "html": {
            FAMILY_TEXT: "HTML (StarWriter)",
            FAMILY_SPREADSHEET: "HTML (StarCalc)",
            FAMILY_PRESENTATION: "impress_html_Export"
        },
        "odt": { FAMILY_TEXT: "writer8" },
        "doc": { FAMILY_TEXT: "MS Word 97" },
        "rtf": { FAMILY_TEXT: "Rich Text Format" },
        "txt": { FAMILY_TEXT: "Text" },
        "docx": { FAMILY_TEXT: "MS Word 2007 XML" },
        "ods": { FAMILY_SPREADSHEET: "calc8" },
        "xls": { FAMILY_SPREADSHEET: "MS Excel 97" },
        "odp": { FAMILY_PRESENTATION: "impress8" },
        "ppt": { FAMILY_PRESENTATION: "MS PowerPoint 97" },
        "swf": { FAMILY_PRESENTATION: "impress_flash_Export" }
    }
    
    class DocumentConverter:
    
        def __init__(self, port=DEFAULT_OPENOFFICE_PORT):
            localContext = uno.getComponentContext()
            resolver = localContext.ServiceManager.createInstanceWithContext("com.sun.star.bridge.UnoUrlResolver", localContext)
            try:
                self.context = resolver.resolve("uno:socket,host=localhost,port=%s;urp;StarOffice.ComponentContext" % port)
            except NoConnectException:
                raise Exception, "failed to connect to OpenOffice.org on port %s" % port
            self.desktop = self.context.ServiceManager.createInstanceWithContext("com.sun.star.frame.Desktop", self.context)
    
        def convert(self, inputFile, outputFile):
    
            inputUrl = self._toFileUrl(inputFile)
            outputUrl = self._toFileUrl(outputFile)
    
            document = self.desktop.loadComponentFromURL(inputUrl, "_blank", 0, self._toProperties(Hidden=True))
            #document.setPropertyValue("DocumentTitle", "saf" ) TODO: Check how this can be set and set doc update mode to  FULL_UPDATE
    
            if self._detectFamily(document) == FAMILY_TEXT:
                indexes = document.getDocumentIndexes()
                for i in range(0, indexes.getCount()):
                    index = indexes.getByIndex(i)
                    index.update()
    
                try:
                    document.refresh()
                except AttributeError:
                    pass
    
                indexes = document.getDocumentIndexes()
                for i in range(0, indexes.getCount()):
                    index = indexes.getByIndex(i)
                    index.update()
    
            outputExt = self._getFileExt(outputFile)
            filterName = self._filterName(document, outputExt)
    
            try:
                document.storeToURL(outputUrl, self._toProperties(FilterName=filterName))
            finally:
                document.close(True)
    
        def _filterName(self, document, outputExt):
            family = self._detectFamily(document)
            try:
                filterByFamily = FILTER_MAP[outputExt]
            except KeyError:
                raise Exception, "unknown output format: '%s'" % outputExt
            try:
                return filterByFamily[family]
            except KeyError:
                raise Exception, "unsupported conversion: from '%s' to '%s'" % (family, outputExt)
    
        def _detectFamily(self, document):
            if document.supportsService("com.sun.star.text.GenericTextDocument"):
                # NOTE: a GenericTextDocument is either a TextDocument, a WebDocument, or a GlobalDocument
                # but this further distinction doesn't seem to matter for conversions
                return FAMILY_TEXT
            if document.supportsService("com.sun.star.sheet.SpreadsheetDocument"):
                return FAMILY_SPREADSHEET
            if document.supportsService("com.sun.star.presentation.PresentationDocument"):
                return FAMILY_PRESENTATION
            if document.supportsService("com.sun.star.drawing.DrawingDocument"):
                return FAMILY_DRAWING
            raise Exception, "unknown document family: %s" % document
    
        def _getFileExt(self, path):
            ext = splitext(path)[1]
            if ext is not None:
                return ext[1:].lower()
    
        def _toFileUrl(self, path):
            return uno.systemPathToFileUrl(abspath(path))
    
        def _toProperties(self, **args):
            props = []
            for key in args:
                prop = PropertyValue()
                prop.Name = key
                prop.Value = args[key]
                props.append(prop)
            return tuple(props)
    
    if __name__ == "__main__":
        from sys import argv, exit
    
        if len(argv) < 3:
            print "USAGE: python %s <input-file> <output-file>" % argv[0]
            exit(255)
        if not isfile(argv[1]):
            print "no such input file: %s" % argv[1]
            exit(1)
    
        try:
            converter = DocumentConverter()    
            converter.convert(argv[1], argv[2])
        except Exception, exception:
            print "ERROR!" + str(exception)
            exit(1)
    

    【讨论】:

    【解决方案2】:

    Java

    我过去曾使用 Apache POI 来解析 Word Documents。它似乎工作得很好。然后这里是some libraries 写到 RTF。

    .Net

    Here's an article 关于在 .Net 中写入 Word 文档。我相信你可以使用同一个库来阅读。

    Python

    Here is an article 用于 Python。

    相关问题

    另外,here is a related if not duplicate question

    【讨论】:

      【解决方案3】:

      看看Docvert。您必须自己设置它,因为我相信该演示只允许您上传打开的办公文档。

      【讨论】:

        【解决方案4】:

        您可以使用 AutoIt 自动打开 Word 中的 XML 文件并保存为 RTF。

        我使用 Word 的用户定义函数将 RTF 文件保存为纯文本以进行转换,效果很好。语法很简单。

        http://www.autoitscript.com/autoit3/index.shtml

        【讨论】:

          【解决方案5】:

          在 java 中,您可以使用 Docmosis 进行转换和可选填充。它位于 openoffice 之上以执行格式转换。如果您安装 openoffice 并手动加载并保存一些示例文档,您将了解格式转换是否适合您。如果是这样,您可以使用 Docmosis 从 Java 驱动它。

          【讨论】: