openoffice安装

openoffice可以在Linux上完成office文件转为pdf文件

安装x window    
  105  yum groupinstall "X Window System"
    2   yum -y install lrzsz ntp bash rsync pciutils dmidecode wget bind-utils  openssh-clients   lftp  telnet gnome-classic-session gnome-terminal nautilus-open-terminal control-center liberation-mono-fonts
    8  cd /usr/local/src/

安装openoffice
   14  tar xvf Apache_OpenOffice_4.1.3_Linux_x86-64_install-rpm_zh-CN.tar.gz 
   15  cd zh-CN/
   16  cd RPMS/
   18  rpm -ivh *
   19  rpm -ivh *.rpm

安装SDK
   22  tar xvf Apache_OpenOffice-SDK_4.1.3_Linux_x86-64_install-rpm_en-US.tar.gz 
   23  cd en-US/
   24  cd RPMS/
   25  rpm -ivh openoffice-sdk-4.1.3-9783.x86_64.rpm 

安装easy_install
   28  wget -q http://peak.telecommunity.com/dist/ez_setup.py
   30  python ez_setup.py 

安装pip
   31  wget https://pypi.python.org/packages/11/b6/abcb525026a4be042b486df43905d6893fb04f05aac21c32c638e939e447/pip-9.0.1.tar.gz#md5=35f01da33009719497f01a4ba69d63c9
   32  tar xvf pip-9.0.1.tar.gz 
   33  cd pip-9.0.1
   34  python setup.py install

安装uno
   35  pip install uno

配置系统服务
   37  vim /etc/init.d/soffice
#!/bin/bash  
# Boot open office so that Alfresco can do transforms.  
# chkconfig: 2345 55 25  
# description: OpenOffice Headless  
#  
# processname: soffice  
# source function library  
. /etc/rc.d/init.d/functions
RETVAL=0
VDISPLAY='99'
SOFFICE_PATH='/opt/openoffice4/program'
SOFFICE_ARGS1="-nofirststartwizard -nologo -headless -display :$VDISPLAY "
SOFFICE_ARGS2='-accept=socket,host=localhost,port=8100;urp;StarOffice.ServiceManager'
SOFFICE_PIDFILE=/var/run/soffice.pid
start_soffice() {
       echo -n $"Starting OpenOffice"  
       $SOFFICE_PATH/soffice $SOFFICE_ARGS1 $SOFFICE_ARGS2 >/dev/null 2>&1 &
       [ $? -eq 0 ] && echo_success || echo_failure
       pidof soffice > $SOFFICE_PIDFILE
       echo  
}
start() {
       start_soffice
}
stop() {
       echo -n $"Stopping OpenOffice"  
       killproc soffice
       echo  
}
case "$1" in
       start)
               start
               ;;
       stop)
               stop
               ;;
       restart)
               stop
               start
               ;;
       *)
               echo $"Usage: $0 {start|stop|restart}"  
esac

   38  chmod 755 /etc/init.d/soffice

安装桌面图形
   80  rpm -ivh openoffice4.1.3-redhat-menus-4.1.3-9783.noarch.rpm 
安装vim和ifconfig
   90  yum install vim *
   91  yum install net-tools.x86_64

安装java
  121  tar xvf jdk-8u65-linux-x64.tar.gz 
  128  cp -r jdk1.8.0_65 /opt/java
  131  vim /etc/profile
export JAVA_HOME=/opt/java/
export JRE_HOME=/opt/java/jre
export CLASSPATH=.:$CLASSPATH:$JAVA_HOME/lib:$JRE_HOME/lib
export PATH=$PATH:$JAVA_HOME/bin:$JRE_HOME/bin
  132  source /etc/profile
  136  java -version

启动服务
   39  /etc/init.d/soffice start

修改 DocumentConverter.py端口
  178  vim DocumentConverter.py 

安装中文支持
  223  yum install kde-l10n-Chinese

上传Windows字体到linux
  335  unzip Fonts.zip 
  338  cd /usr/share/fonts/
  339  ln -s /data0/Fonts win7fonts
  340  cd win7fonts/
  343  yum install mkfontscale
  344  mkfontscale
  345  mkfontdir
  346  fc-cache

重启
  354  reboot 
  356  cd /usr/share/fonts/
  359  cd win7fonts/
  361  fc-cache
  362  /etc/init.d/soffice start
  363  cd /data0/pdf/
  366  /opt/openoffice4/program/python DocumentConverter.py a.xlsx 1.pdf

DocumentConverter.py

#
# PyODConverter (Python OpenDocument Converter) v1.1 - 2009-11-14
#
# This script converts a document from one office format to another by
# connecting to an OpenOffice.org instance via Python-UNO bridge.
#
# Copyright (C) 2008-2009 Mirko Nasato <mirko@artofsolving.com>
# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl-2.1.html
# - or any later version.
#
DEFAULT_OPENOFFICE_PORT = 8100

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_WEB = "Web"
FAMILY_SPREADSHEET = "Spreadsheet"
FAMILY_PRESENTATION = "Presentation"
FAMILY_DRAWING = "Drawing"

#---------------------#
# Configuration Start #
#---------------------#

# see http://wiki.services.openoffice.org/wiki/Framework/Article/Filter

# most formats are auto-detected; only those requiring options are defined here
IMPORT_FILTER_MAP = {
    "txt": {
        "FilterName": "Text (encoded)",
        "FilterOptions": "utf8"
    },
    "csv": {
        "FilterName": "Text - txt - csv (StarCalc)",
        "FilterOptions": "44,34,0"
    }
}

EXPORT_FILTER_MAP = {
    "pdf": {
        FAMILY_TEXT: { "FilterName": "writer_pdf_Export" },
        FAMILY_WEB: { "FilterName": "writer_web_pdf_Export" },
        FAMILY_SPREADSHEET: { "FilterName": "calc_pdf_Export" },
        FAMILY_PRESENTATION: { "FilterName": "impress_pdf_Export" },
        FAMILY_DRAWING: { "FilterName": "draw_pdf_Export" }
    },
    "html": {
        FAMILY_TEXT: { "FilterName": "HTML (StarWriter)" },
        FAMILY_SPREADSHEET: { "FilterName": "HTML (StarCalc)" },
        FAMILY_PRESENTATION: { "FilterName": "impress_html_Export" }
    },
    "odt": {
        FAMILY_TEXT: { "FilterName": "writer8" },
        FAMILY_WEB: { "FilterName": "writerweb8_writer" }
    },
    "doc": {
        FAMILY_TEXT: { "FilterName": "MS Word 97" }
    },
    "rtf": {
        FAMILY_TEXT: { "FilterName": "Rich Text Format" }
    },
    "txt": {
        FAMILY_TEXT: {
            "FilterName": "Text",
            "FilterOptions": "utf8"
        }
    },
    "ods": {
        FAMILY_SPREADSHEET: { "FilterName": "calc8" }
    },
    "xls": {
        FAMILY_SPREADSHEET: { "FilterName": "MS Excel 97" }
    },
    "csv": {
        FAMILY_SPREADSHEET: {
            "FilterName": "Text - txt - csv (StarCalc)",
            "FilterOptions": "44,34,0"
        }
    },
    "odp": {
        FAMILY_PRESENTATION: { "FilterName": "impress8" }
    },
    "ppt": {
        FAMILY_PRESENTATION: { "FilterName": "MS PowerPoint 97" }
    },
    "swf": {
        FAMILY_DRAWING: { "FilterName": "draw_flash_Export" },
        FAMILY_PRESENTATION: { "FilterName": "impress_flash_Export" }
    }
}

PAGE_STYLE_OVERRIDE_PROPERTIES = {
    FAMILY_SPREADSHEET: {
        #--- Scale options: uncomment 1 of the 3 ---
        # a) 'Reduce / enlarge printout': 'Scaling factor'
        "PageScale": 100,
        # b) 'Fit print range(s) to width / height': 'Width in pages' and 'Height in pages'
        #"ScaleToPagesX": 1, "ScaleToPagesY": 1000,
        # c) 'Fit print range(s) on number of pages': 'Fit print range(s) on number of pages'
        #"ScaleToPages": 1,
        "PrintGrid": False
    }
}

#-------------------#
# Configuration End #
#-------------------#

class DocumentConversionException(Exception):

    def __init__(self, message):
        self.message = message

    def __str__(self):
        return self.message


class DocumentConverter:
    
    def __init__(self, port=DEFAULT_OPENOFFICE_PORT):
        localContext = uno.getComponentContext()
        resolver = localContext.ServiceManager.createInstanceWithContext("com.sun.star.bridge.UnoUrlResolver", localContext)
        try:
            context = resolver.resolve("uno:socket,host=localhost,port=%s;urp;StarOffice.ComponentContext" % port)
        except NoConnectException:
            raise DocumentConversionException, "failed to connect to OpenOffice.org on port %s" % port
        self.desktop = context.ServiceManager.createInstanceWithContext("com.sun.star.frame.Desktop", context)

    def convert(self, inputFile, outputFile):

        inputUrl = self._toFileUrl(inputFile)
        outputUrl = self._toFileUrl(outputFile)

        loadProperties = { "Hidden": True }
        inputExt = self._getFileExt(inputFile)
        if IMPORT_FILTER_MAP.has_key(inputExt):
            loadProperties.update(IMPORT_FILTER_MAP[inputExt])
        
        document = self.desktop.loadComponentFromURL(inputUrl, "_blank", 0, self._toProperties(loadProperties))
        try:
            document.refresh()
        except AttributeError:
            pass

        family = self._detectFamily(document)
        self._overridePageStyleProperties(document, family)
        
        outputExt = self._getFileExt(outputFile)
        storeProperties = self._getStoreProperties(document, outputExt)

        try:
            document.storeToURL(outputUrl, self._toProperties(storeProperties))
        finally:
            document.close(True)

    def _overridePageStyleProperties(self, document, family):
        if PAGE_STYLE_OVERRIDE_PROPERTIES.has_key(family):
            properties = PAGE_STYLE_OVERRIDE_PROPERTIES[family]
            pageStyles = document.getStyleFamilies().getByName('PageStyles')
            for styleName in pageStyles.getElementNames():
                pageStyle = pageStyles.getByName(styleName)
                for name, value in properties.items():
                    pageStyle.setPropertyValue(name, value)

    def _getStoreProperties(self, document, outputExt):
        family = self._detectFamily(document)
        try:
            propertiesByFamily = EXPORT_FILTER_MAP[outputExt]
        except KeyError:
            raise DocumentConversionException, "unknown output format: '%s'" % outputExt
        try:
            return propertiesByFamily[family]
        except KeyError:
            raise DocumentConversionException, "unsupported conversion: from '%s' to '%s'" % (family, outputExt)
    
    def _detectFamily(self, document):
        if document.supportsService("com.sun.star.text.WebDocument"):
            return FAMILY_WEB
        if document.supportsService("com.sun.star.text.GenericTextDocument"):
            # must be TextDocument or GlobalDocument
            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 DocumentConversionException, "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, dict):
        props = []
        for key in dict:
            prop = PropertyValue()
            prop.Name = key
            prop.Value = dict[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 DocumentConversionException, exception:
        print "ERROR! " + str(exception)
        exit(1)
    except ErrorCodeIOException, exception:
        print "ERROR! ErrorCodeIOException %d" % exception.ErrCode
        exit(1)