如何将POI数据高效生成Word文档？
摘要：通过配置word模板生成相应的word文档。支持文字，列表，原样式输出。采用java poi 开源库。
p, blockquote, ul, ol, dl, table, pre { margin: 15px 0 }
h1, h2, h3, h4, h5, h6 { margin: 20px 0 10px; padding: 0; font-weight: bold; -webkit-font-smoothing: antialiased }
h1 tt, h1 code, h2 tt, h2 code, h3 tt, h3 code, h4 tt, h4 code, h5 tt, h5 code, h6 tt, h6 code { font-size: inherit }
h1 { font-size: 28px; color: rgba(0, 0, 0, 1) }
h2 { font-size: 24px; border-bottom: 1px solid rgba(204, 204, 204, 1); color: rgba(0, 0, 0, 1) }
h3 { font-size: 18px }
h4 { font-size: 16px }
h5 { font-size: 14px }
h6 { color: rgba(119, 119, 119, 1); font-size: 14px }
body>h2:first-child, body>h1:first-child, body>h1:first-child+h2, body>h3:first-child, body>h4:first-child, body>h5:first-child, body>h6:first-child { margin-top: 0; padding-top: 0 }
a:first-child h1, a:first-child h2, a:first-child h3, a:first-child h4, a:first-child h5, a:first-child h6 { margin-top: 0; padding-top: 0 }
h1+p, h2+p, h3+p, h4+p, h5+p, h6+p { margin-top: 10px }
a { color: rgba(65, 131, 196, 1); text-decoration: none }
a:hover { text-decoration: underline }
ul, ol { padding-left: 30px }
ul li>:first-child, ol li>:first-child, ul li ul:first-of-type, ol li ol:first-of-type, ul li ol:first-of-type, ol li ul:first-of-type { margin-top: 0 }
ul ul, ul ol, ol ol, ol ul { margin-bottom: 0 }
dl { padding: 0 }
dl dt { font-size: 14px; font-weight: bold; font-style: italic; padding: 0; margin: 15px 0 5px }
dl dt:first-child { padding: 0 }
dl dt>:first-child { margin-top: 0 }
dl dt>:last-child { margin-bottom: 0 }
dl dd { margin: 0 0 15px; padding: 0 15px }
dl dd>:first-child { margin-top: 0 }
dl dd>:last-child { margin-bottom: 0 }
pre, code, tt { font-size: 12px; font-family: Consolas, "Liberation Mono", Courier, monospace }
code, tt { margin: 0; padding: 0; white-space: nowrap; border: 1px solid rgba(234, 234, 234, 1); background-color: rgba(248, 248, 248, 1); border-radius: 3px }
pre>code { margin: 0; padding: 0; white-space: pre; border: none; background: rgba(0, 0, 0, 0) }
pre { background-color: rgba(248, 248, 248, 1); border: 1px solid rgba(204, 204, 204, 1); font-size: 13px; line-height: 19px; overflow: auto; padding: 6px 10px; border-radius: 3px }
pre code, pre tt { background-color: rgba(0, 0, 0, 0); border: none }
kbd { -moz-border-bottom-colors: none; -moz-border-left-colors: none; -moz-border-right-colors: none; -moz-border-top-colors: none; background-color: rgba(221, 221, 221, 1); background-image: linear-gradient(rgba(241, 241, 241, 1), rgba(221, 221, 221, 1)); background-repeat: repeat-x; border-top: 1px solid rgba(221, 221, 221, 1); border-right: 1px solid rgba(204, 204, 204, 1); border-bottom: 1px solid rgba(204, 204, 204, 1); border-left: 1px solid rgba(221, 221, 221, 1); border-image: none; border-radius: 2px; font-family: "Helvetica Neue", Helvetica, Arial, sans-serif; line-height: 10px; padding: 1px 4px }
blockquote { border-left: 4px solid rgba(221, 221, 221, 1); padding: 0 15px; color: rgba(119, 119, 119, 1) }
blockquote>:first-child { margin-top: 0 }
blockquote>:last-child { margin-bottom: 0 }
hr { clear: both; margin: 15px 0; height: 0; overflow: hidden; border-top: none; border-right: none; border-bottom: 4px solid rgba(221, 221, 221, 1); border-left: none; background: rgba(0, 0, 0, 0); padding: 0 }
img { max-width: 100% }
.highlight { background: rgba(255, 255, 255, 1) }
.highlight .c { color: rgba(153, 153, 136, 1); font-style: italic }
.highlight .err { color: rgba(166, 23, 23, 1); background-color: rgba(227, 210, 210, 1) }
.highlight .k { font-weight: bold }
.highlight .o { font-weight: bold }
.highlight .cm { color: rgba(153, 153, 136, 1); font-style: italic }
.highlight .cp { color: rgba(153, 153, 153, 1); font-weight: bold }
.highlight .c1 { color: rgba(153, 153, 136, 1); font-style: italic }
.highlight .cs { color: rgba(153, 153, 153, 1); font-weight: bold; font-style: italic }
.highlight .gd { color: rgba(0, 0, 0, 1); background-color: rgba(255, 221, 221, 1) }
.highlight .gd .x { color: rgba(0, 0, 0, 1); background-color: rgba(255, 170, 170, 1) }
.highlight .ge { font-style: italic }
.highlight .gr { color: rgba(170, 0, 0, 1) }
.highlight .gh { color: rgba(153, 153, 153, 1) }
.highlight .gi { color: rgba(0, 0, 0, 1); background-color: rgba(221, 255, 221, 1) }
.highlight .gi .x { color: rgba(0, 0, 0, 1); background-color: rgba(170, 255, 170, 1) }
.highlight .go { color: rgba(136, 136, 136, 1) }
.highlight .gp { color: rgba(85, 85, 85, 1) }
.highlight .gs { font-weight: bold }
.highlight .gu { color: rgba(170, 170, 170, 1) }
.highlight .gt { color: rgba(170, 0, 0, 1) }
.highlight .kc { font-weight: bold }
.highlight .kd { font-weight: bold }
.highlight .kp { font-weight: bold }
.highlight .kr { font-weight: bold }
.highlight .kt { color: rgba(68, 85, 136, 1); font-weight: bold }
.highlight .m { color: rgba(0, 153, 153, 1) }
.highlight .s { color: rgba(221, 17, 68, 1) }
.highlight .na { color: rgba(0, 128, 128, 1) }
.highlight .nb { color: rgba(0, 134, 179, 1) }
.highlight .nc { color: rgba(68, 85, 136, 1); font-weight: bold }
.highlight .no { color: rgba(0, 128, 128, 1) }
.highlight .ni { color: rgba(128, 0, 128, 1) }
.highlight .ne { color: rgba(153, 0, 0, 1); font-weight: bold }
.highlight .nf { color: rgba(153, 0, 0, 1); font-weight: bold }
.highlight .nn { color: rgba(85, 85, 85, 1) }
.highlight .nt { color: rgba(0, 0, 128, 1) }
.highlight .nv { color: rgba(0, 128, 128, 1) }
.highlight .ow { font-weight: bold }
.highlight .w { color: rgba(187, 187, 187, 1) }
.highlight .mf { color: rgba(0, 153, 153, 1) }
.highlight .mh { color: rgba(0, 153, 153, 1) }
.highlight .mi { color: rgba(0, 153, 153, 1) }
.highlight .mo { color: rgba(0, 153, 153, 1) }
.highlight .sb { color: rgba(221, 17, 68, 1) }
.highlight .sc { color: rgba(221, 17, 68, 1) }
.highlight .sd { color: rgba(221, 17, 68, 1) }
.highlight .s2 { color: rgba(221, 17, 68, 1) }
.highlight .se { color: rgba(221, 17, 68, 1) }
.highlight .sh { color: rgba(221, 17, 68, 1) }
.highlight .si { color: rgba(221, 17, 68, 1) }
.highlight .sx { color: rgba(221, 17, 68, 1) }
.highlight .sr { color: rgba(0, 153, 38, 1) }
.highlight .s1 { color: rgba(221, 17, 68, 1) }
.highlight .ss { color: rgba(153, 0, 115, 1) }
.highlight .bp { color: rgba(153, 153, 153, 1) }
.highlight .vc { color: rgba(0, 128, 128, 1) }
.highlight .vg { color: rgba(0, 128, 128, 1) }
.highlight .vi { color: rgba(0, 128, 128, 1) }
.highlight .il { color: rgba(0, 153, 153, 1) }
.pl-c { color: rgba(150, 152, 150, 1) }
.pl-c1, .pl-mdh, .pl-mm, .pl-mp, .pl-mr, .pl-s1 .pl-v, .pl-s3, .pl-sc, .pl-sv { color: rgba(0, 134, 179, 1) }
.pl-e, .pl-en { color: rgba(121, 93, 163, 1) }
.pl-s1 .pl-s2, .pl-smi, .pl-smp, .pl-stj, .pl-vo, .pl-vpf { color: rgba(51, 51, 51, 1) }
.pl-ent { color: rgba(99, 163, 92, 1) }
.pl-k, .pl-s, .pl-st { color: rgba(167, 29, 93, 1) }
.pl-pds, .pl-s1, .pl-s1 .pl-pse .pl-s2, .pl-sr, .pl-sr .pl-cce, .pl-sr .pl-sra, .pl-sr .pl-sre, .pl-src, .pl-v { color: rgba(223, 80, 0, 1) }
.pl-id { color: rgba(181, 42, 29, 1) }
.pl-ii { background-color: rgba(181, 42, 29, 1); color: rgba(248, 248, 248, 1) }
.pl-sr .pl-cce { color: rgba(99, 163, 92, 1); font-weight: bold }
.pl-ml { color: rgba(105, 58, 23, 1) }
.pl-mh, .pl-mh .pl-en, .pl-ms { color: rgba(29, 62, 129, 1); font-weight: bold }
.pl-mq { color: rgba(0, 128, 128, 1) }
.pl-mi { color: rgba(51, 51, 51, 1); font-style: italic }
.pl-mb { color: rgba(51, 51, 51, 1); font-weight: bold }
.pl-md, .pl-mdhf { background-color: rgba(255, 236, 236, 1); color: rgba(189, 44, 0, 1) }
.pl-mdht, .pl-mi1 { background-color: rgba(234, 255, 234, 1); color: rgba(85, 165, 50, 1) }
.pl-mdr { color: rgba(121, 93, 163, 1); font-weight: bold }
.pl-mo { color: rgba(29, 62, 129, 1) }
.task-list { padding-left: 10px; margin-bottom: 0 }
.task-list li { margin-left: 20px }
.task-list-item { list-style-type: none; padding-left: 10px }
.task-list-item label { font-weight: 400 }
.task-list-item.enabled label { cursor: pointer }
.task-list-item+.task-list-item { margin-top: 3px }
.task-list-item-checkbox { display: inline-block; margin-left: -20px; margin-right: 3px; vertical-align: 1px }
POI生成WORD文档
POI为Java系处理office文档的比较优秀的开源库，其中对于Excel的处理最为优秀，文档也写的很详细。不过很多网友都认为它在word文档处理方面就逊色很多，不过对于我本次的完成文档的生成我依然选择了POI。添加微信回复POI邀请你加群
需要完成功能
配置Word模板文件，包括表格
解析配置的Word文档，返回配置的特殊标记
构造数据，替换配置的标签，以及生成表格
配置word模版
采用${xx}方式配置标签，如果是表格在对应一行一列配置表格名称
注意在word文档中，如果两个相近的字符样式不同，word默认会保存在不同的RUN元素中，由此很多朋友在配置好以后都需要保存为一个单独的文件，然后不把不在一起的标签合并到一个RUN元素中，如果文件比较大，我相信这绝对是一个比较痛苦的事情，这里将会侧重处理这个问题.我的解决方案是只保留第一RUN的样式其他的删掉
解析word模板
首先需要将文件转换为XWPFDocument对象，可以通过流的当时，也可以通过opcpackage,不过如果使用opcpackage打开的方式，打开的文件和最终生成的文件不能够是同一个文件，我这里采用文件流的方式
public XWPFDocument openDocument() {
XWPFDocument xdoc = null;
InputStream is = null;
try {
is = new FileInputStream(saveFile);
xdoc = new XWPFDocument(is);
} catch (IOException e) {
e.printStackTrace();
}
return xdoc;
}
获取非列表的标签，实现方式XWPFDocument对象有当前所有段落以及表格，这里暂不考虑表格嵌套表格的情况，每个段落的文本信息是可以通过p.getText()获取，获取段落中文档配置信息如下：
// 获取段落集合中所有文本
public List<TagInfo> getWordTag(XWPFDocument doc, String regex) {
List<TagInfo> tags = new ArrayList<TagInfo>();
// 普通段落
List<XWPFParagraph> pars = doc.getParagraphs();
for (int i = 0; i < pars.size(); i++) {
XWPFParagraph p = pars.get(i);
setTagInfoList(tags, p, regex);
}
// Table中段落
List<XWPFTable> commTables = getDocTables(doc, false, regex);
for (XWPFTable table : commTables) {
List<XWPFParagraph> tparags = getTableParagraph(table);
for (int i = 0; i < tparags.size(); i++) {
XWPFParagraph p = tparags.get(i);
setTagInfoList(tags, p, regex);
}
}
return tags;
}
获取文本后通过正则解析，并依次保存到TagInfo中
// 向 taglist中添加新解析的段落信息
private void setTagInfoList(List<TagInfo> list, XWPFParagraph p,
String regex) {
if (regex == "")
regex = defaultRegex;
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(p.getText());
int startPosition = 0;
while (matcher.find(startPosition)) {
String match = matcher.group();
if (!list.contains(new TagInfo(match, match, ""))) {
list.add(new TagInfo(match, match, ""));
}
startPosition = matcher.end();
}
}
解析表格
// 获取Table列表中的配置信息
public Map<String, List<List<TagInfo>>> getTableTag(XWPFDocument doc,
String regex) {
Map<String, List<List<TagInfo>>> mapList = new HashMap<String, List<List<TagInfo>>>();
List<XWPFTable> lstTables = getDocTables(doc, true, regex);
for (XWPFTable table : lstTables) {
// 获取每个表格第一个单元格，以及最后一行
String strTableName = getTableListName(table, regex);
List<List<TagInfo>> list = new ArrayList<List<TagInfo>>();
List<TagInfo> lstTag = new ArrayList<TagInfo>();
int rowSize = table.getRows().size();
XWPFTableRow lastRow = table.getRow(rowSize - 1);
for (XWPFTableCell cell : lastRow.getTableCells()) {
for (XWPFParagraph p : cell.getParagraphs()) {
// 去掉空白字符串
if (p.getText() != null && p.getText().length() > 0) {
setTagInfoList(lstTag, p, regex);
}
}
}
list.add(lstTag);
// 添加到数据集
mapList.put(strTableName, list);
}
return mapList;
}
生成WORD文档
难点替换标签
传入数据格式包含三个formtag以及一个tableTag
{"formTags":
[{"TagName":"${xxxx}","TagText":"${xxxx}","TagValue":""},
{"TagName":"${123}","TagText":"${123}","TagValue":""},
{"TagName":"${ddd}","TagText":"${ddd}","TagValue":""}],
"tableTags":{
"${table}":[
[{"TagName":"${COL1}","TagText":"${COL1}","TagValue":""},{"TagName":"${COL2}","TagText":"${COL2}","TagValue":""}]
]}
}
普通文档生成，并且保留配置样式，这里主要使用POI中提供searchText方法，返回Tag所有所在的RUN标签，通过一个字符做比较，如果找的第一个匹配的文本开始计数，所有在当前条件下类型 $${xxx}这样的标签是无法实现替换的
替换普通文本Tag
public void ReplaceInParagraph(List<TagInfo> tagList, XWPFParagraph para,
String regex) {
if (regex == "")
regex = defaultRegex;
List<XWPFRun> runs = para.getRuns();
for (TagInfo ti : tagList) {
String find = ti.TagText;
String replValue = ti.TagValue;
TextSegement found = para.searchText(find,
new PositionInParagraph());
if (found != null) {
// 判断查找内容是否在同一个Run标签中
if (found.getBeginRun() == found.getEndRun()) {
XWPFRun run = runs.get(found.getBeginRun());
String runText = run.getText(run.getTextPosition());
String replaced = runText.replace(find, replValue);
run.setText(replaced, 0);
} else {
// 存在多个Run标签
StringBuilder sb = new StringBuilder();
for (int runPos = found.getBeginRun(); runPos <= found
.getEndRun(); runPos++) {
XWPFRun run = runs.get(runPos);
sb.append(run.getText((run.getTextPosition())));
}
String connectedRuns = sb.toString();
String replaced = connectedRuns.replace(find, replValue);
XWPFRun firstRun = runs.get(found.getBeginRun());
firstRun.setText(replaced, 0);
// 删除后边的run标签
for (int runPos = found.getBeginRun() + 1; runPos <= found
.getEndRun(); runPos++) {
// 清空其他标签内容
XWPFRun partNext = runs.get(runPos);
partNext.setText("", 0);
}
}
}
}
// 完成第一遍查找,检测段落中的标签是否已经替换完
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(para.getText());
boolean find = matcher.find();
if (find) {
ReplaceInParagraph(tagList, para, regex);
find = false;
}
}
表格主要是通过复制模版行，然后对模版行中的内容做修改
复制文本标签RUN
private void CopyRun(XWPFRun target, XWPFRun source) {
target.getCTR().setRPr(source.getCTR().getRPr());
// 设置文本
target.setText(source.text());
}
复制段落XWPFParagraph
private void copyParagraph(XWPFParagraph target, XWPFParagraph source) {
// 设置段落样式
target.getCTP().setPPr(source.getCTP().getPPr());
// 添加Run标签
for (int pos = 0; pos < target.getRuns().size(); pos++) {
target.removeRun(pos);
}
for (XWPFRun s : source.getRuns()) {
XWPFRun targetrun = target.createRun();
CopyRun(targetrun, s);
}
}
复制单元格XWPFTableCell
private void copyTableCell(XWPFTableCell target, XWPFTableCell source) {
// 列属性
target.getCTTc().setTcPr(source.getCTTc().getTcPr());
// 删除目标 targetCell 所有单元格
for (int pos = 0; pos < target.getParagraphs().size(); pos++) {
target.removeParagraph(pos);
}
// 添加段落
for (XWPFParagraph sp : source.getParagraphs()) {
XWPFParagraph targetP = target.addParagraph();
copyParagraph(targetP, sp);
}
}
复制行XWPFTableRow
private void CopytTableRow(XWPFTableRow target, XWPFTableRow source) {
// 复制样式
target.getCtRow().setTrPr(source.getCtRow().getTrPr());
// 复制单元格
for (int i = 0; i < target.getTableCells().size(); i++) {
copyTableCell(target.getCell(i), source.getCell(i));
}
}
以上就完成所有功能更，只要你配置规范，可以完全原样输出模版内容。这里特别感谢下肖哥哥大力支持。
其次，java的编码真的让人很无语，get或post时中文各种乱码