⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 xmlreader.html

📁 解析RSS工具源码
💻 HTML
📖 第 1 页 / 共 4 页
字号:
<a name="436" href="#436">436</a> <a name="437" href="#437">437</a>     <em class="comment">// returns charset parameter value, NULL if not present, NULL if httpContentType is NULL</em><a name="438" href="#438">438</a>     <strong>private</strong> <strong>static</strong> String getContentTypeEncoding(String httpContentType) {<a name="439" href="#439">439</a>         String encoding = <strong>null</strong>;<a name="440" href="#440">440</a>         <strong>if</strong> (httpContentType!=<strong>null</strong>) {<a name="441" href="#441">441</a>             <strong>int</strong> i = httpContentType.indexOf(<span class="string">";"</span>);<a name="442" href="#442">442</a>             <strong>if</strong> (i>-1) {<a name="443" href="#443">443</a>                 String postMime = httpContentType.substring(i+1);<a name="444" href="#444">444</a>                 Matcher m = CHARSET_PATTERN.matcher(postMime);<a name="445" href="#445">445</a>                 encoding = (m.find()) ? m.group(1) : <strong>null</strong>;<a name="446" href="#446">446</a>                 encoding = (encoding!=<strong>null</strong>) ? encoding.toUpperCase() : <strong>null</strong>;<a name="447" href="#447">447</a>             }<a name="448" href="#448">448</a>         }<a name="449" href="#449">449</a>         <strong>return</strong> encoding;<a name="450" href="#450">450</a>     }<a name="451" href="#451">451</a> <a name="452" href="#452">452</a>     <em class="comment">// returns the BOM in the stream, NULL if not present,</em><a name="453" href="#453">453</a>     <em class="comment">// if there was BOM the in the stream it is consumed</em><a name="454" href="#454">454</a>     <strong>private</strong> <strong>static</strong> String getBOMEncoding(PushbackInputStream is) throws IOException {<a name="455" href="#455">455</a>         String encoding = <strong>null</strong>;<a name="456" href="#456">456</a>         <strong>int</strong>[] bytes = <strong>new</strong> <strong>int</strong>[3];<a name="457" href="#457">457</a>         bytes[0] = is.read();<a name="458" href="#458">458</a>         bytes[1] = is.read();<a name="459" href="#459">459</a>         bytes[2] = is.read();<a name="460" href="#460">460</a> <a name="461" href="#461">461</a>         <strong>if</strong> (bytes[0] == 0xFE &amp;&amp; bytes[1] == 0xFF) {<a name="462" href="#462">462</a>             encoding = UTF_16BE;<a name="463" href="#463">463</a>             is.unread(bytes[2]);<a name="464" href="#464">464</a>         }<a name="465" href="#465">465</a>         <strong>else</strong><a name="466" href="#466">466</a>         <strong>if</strong> (bytes[0] == 0xFF &amp;&amp; bytes[1] == 0xFE) {<a name="467" href="#467">467</a>             encoding = UTF_16LE;<a name="468" href="#468">468</a>             is.unread(bytes[2]);<a name="469" href="#469">469</a>         }<a name="470" href="#470">470</a>         <strong>else</strong><a name="471" href="#471">471</a>         <strong>if</strong> (bytes[0] == 0xEF &amp;&amp; bytes[1] == 0xBB &amp;&amp; bytes[2] == 0xBF) {<a name="472" href="#472">472</a>             encoding = UTF_8;<a name="473" href="#473">473</a>         }<a name="474" href="#474">474</a>         <strong>else</strong> {<a name="475" href="#475">475</a>             <strong>for</strong> (<strong>int</strong> i=bytes.length-1;i>=0;i--) {<a name="476" href="#476">476</a>                 is.unread(bytes[i]);<a name="477" href="#477">477</a>             }<a name="478" href="#478">478</a>         }<a name="479" href="#479">479</a>         <strong>return</strong> encoding;<a name="480" href="#480">480</a>     }<a name="481" href="#481">481</a> <a name="482" href="#482">482</a>     <em class="comment">// returns the best guess for the encoding by looking the first bytes of the stream, '&lt;?'</em><a name="483" href="#483">483</a>     <strong>private</strong> <strong>static</strong> String getXMLGuessEncoding(PushbackInputStream is) throws IOException {<a name="484" href="#484">484</a>         String encoding = <strong>null</strong>;<a name="485" href="#485">485</a>         <strong>int</strong>[] bytes = <strong>new</strong> <strong>int</strong>[4];<a name="486" href="#486">486</a>         bytes[0] = is.read();<a name="487" href="#487">487</a>         bytes[1] = is.read();<a name="488" href="#488">488</a>         bytes[2] = is.read();<a name="489" href="#489">489</a>         bytes[3] = is.read();<a name="490" href="#490">490</a>         <strong>for</strong> (<strong>int</strong> i=bytes.length-1;i>=0;i--) {<a name="491" href="#491">491</a>             is.unread(bytes[i]);<a name="492" href="#492">492</a>         }<a name="493" href="#493">493</a> <a name="494" href="#494">494</a>         <strong>if</strong> (bytes[0] == 0x00 &amp;&amp; bytes[1] == 0x3C &amp;&amp; bytes[2] == 0x00 &amp;&amp; bytes[3] == 0x3F) {<a name="495" href="#495">495</a>                 encoding = UTF_16BE;<a name="496" href="#496">496</a>         }<a name="497" href="#497">497</a>         <strong>else</strong><a name="498" href="#498">498</a>         <strong>if</strong> (bytes[0] == 0x3C &amp;&amp; bytes[1] == 0x00 &amp;&amp; bytes[2] == 0x3F &amp;&amp; bytes[3] == 0x00) {<a name="499" href="#499">499</a>                 encoding = UTF_16LE;<a name="500" href="#500">500</a>         }<a name="501" href="#501">501</a>         <strong>else</strong><a name="502" href="#502">502</a>         <strong>if</strong> (bytes[0] == 0x3C &amp;&amp; bytes[1] == 0x3F &amp;&amp; bytes[2] == 0x78 &amp;&amp; bytes[3] == 0x6D) {<a name="503" href="#503">503</a>             encoding = UTF_8;<a name="504" href="#504">504</a>         }<a name="505" href="#505">505</a>         <strong>return</strong> encoding;<a name="506" href="#506">506</a>     }<a name="507" href="#507">507</a> <a name="508" href="#508">508</a> <a name="509" href="#509">509</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Pattern ENCODING_PATTERN =<a name="510" href="#510">510</a>         Pattern.compile(<span class="string">"&lt;&#47;&#47;?xml.*encoding[&#47;&#47;s]*=[&#47;&#47;s]*((?:\&quot;.[^\&quot;]*\&quot;)|(?:'.[^']*')).*&#47;&#47;?>"</span>, Pattern.MULTILINE);<a name="511" href="#511">511</a> <a name="512" href="#512">512</a>     <em class="comment">// returns the encoding declared in the &lt;?xml encoding=...?>,  NULL if none</em><a name="513" href="#513">513</a>     <strong>private</strong> <strong>static</strong> String getXmlProlog(PushbackInputStream is,String guessedEnc) throws IOException {<a name="514" href="#514">514</a>         String encoding = <strong>null</strong>;<a name="515" href="#515">515</a>         <strong>if</strong> (guessedEnc!=<strong>null</strong>) {<a name="516" href="#516">516</a>             byte[] bytes = <strong>new</strong> byte[PUSHBACK_MAX_SIZE];<a name="517" href="#517">517</a>             <strong>int</strong> offset = 0;<a name="518" href="#518">518</a>             <strong>int</strong> max = PUSHBACK_MAX_SIZE;<a name="519" href="#519">519</a>             <strong>int</strong> c = is.read(bytes,offset,max);<a name="520" href="#520">520</a>             <strong>while</strong> (c!=-1 &amp;&amp; offset&lt;PUSHBACK_MAX_SIZE) {<a name="521" href="#521">521</a>                 offset += c;<a name="522" href="#522">522</a>                 max -= c;<a name="523" href="#523">523</a>                 c = is.read(bytes,offset,max);<a name="524" href="#524">524</a>             }<a name="525" href="#525">525</a>             <strong>int</strong> bytesRead = offset;<a name="526" href="#526">526</a>             <strong>if</strong> (bytesRead>0) {<a name="527" href="#527">527</a>                 is.unread(bytes,0,bytesRead);<a name="528" href="#528">528</a>                 Reader reader = <strong>new</strong> InputStreamReader(<strong>new</strong> ByteArrayInputStream(bytes,0,bytesRead), guessedEnc);<a name="529" href="#529">529</a>                 BufferedReader br = <strong>new</strong> BufferedReader(reader);<a name="530" href="#530">530</a>                 StringBuffer prolog = <strong>new</strong> StringBuffer(PUSHBACK_MAX_SIZE);<a name="531" href="#531">531</a>                 String line = br.readLine();<a name="532" href="#532">532</a>                 <strong>while</strong> (line != <strong>null</strong>) {<a name="533" href="#533">533</a>                   prolog.append(line).append(<span class="string">"\n"</span>);<a name="534" href="#534">534</a>                   line = br.readLine();<a name="535" href="#535">535</a>                 }<a name="536" href="#536">536</a>                 Matcher m = ENCODING_PATTERN.matcher(prolog);<a name="537" href="#537">537</a>                 <strong>if</strong> (m.find()) {<a name="538" href="#538">538</a>                     encoding = m.group(1).toUpperCase();<a name="539" href="#539">539</a>                     encoding = encoding.substring(1,encoding.length()-1);<a name="540" href="#540">540</a>                 }<a name="541" href="#541">541</a>             }<a name="542" href="#542">542</a>         }<a name="543" href="#543">543</a>         <strong>return</strong> encoding;<a name="544" href="#544">544</a>     }<a name="545" href="#545">545</a> <a name="546" href="#546">546</a>     <em class="comment">// indicates if the MIME type belongs to the APPLICATION XML family</em><a name="547" href="#547">547</a>     <strong>private</strong> <strong>static</strong> <strong>boolean</strong> isAppXml(String mime) {<a name="548" href="#548">548</a>         <strong>return</strong> mime!=<strong>null</strong> &amp;&amp;<a name="549" href="#549">549</a>                (mime.equals(<span class="string">"application/xml"</span>) ||<a name="550" href="#550">550</a>                 mime.equals(<span class="string">"application/xml-dtd"</span>) ||<a name="551" href="#551">551</a>                 mime.equals(<span class="string">"application/xml-external-parsed-entity"</span>) ||<a name="552" href="#552">552</a>                 (mime.startsWith(<span class="string">"application/"</span>) &amp;&amp; mime.endsWith(<span class="string">"+xml"</span>)));<a name="553" href="#553">553</a>     }<a name="554" href="#554">554</a> <a name="555" href="#555">555</a>     <em class="comment">// indicates if the MIME type belongs to the TEXT XML family</em><a name="556" href="#556">556</a>     <strong>private</strong> <strong>static</strong> <strong>boolean</strong> isTextXml(String mime) {<a name="557" href="#557">557</a>         <strong>return</strong> mime!=<strong>null</strong> &amp;&amp;<a name="558" href="#558">558</a>                (mime.equals(<span class="string">"text/xml"</span>) ||<a name="559" href="#559">559</a>                 mime.equals(<span class="string">"text/xml-external-parsed-entity"</span>) ||<a name="560" href="#560">560</a>                 (mime.startsWith(<span class="string">"text/"</span>) &amp;&amp; mime.endsWith(<span class="string">"+xml"</span>)));<a name="561" href="#561">561</a>     }<a name="562" href="#562">562</a> <a name="563" href="#563">563</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> MessageFormat RAW_EX_1 = <strong>new</strong> MessageFormat(<a name="564" href="#564">564</a>             <span class="string">"Invalid encoding, BOM [{0}] XML guess [{1}] XML prolog [{2}] encoding mismatch"</span>);<a name="565" href="#565">565</a> <a name="566" href="#566">566</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> MessageFormat RAW_EX_2 = <strong>new</strong> MessageFormat(<a name="567" href="#567">567</a>             <span class="string">"Invalid encoding, BOM [{0}] XML guess [{1}] XML prolog [{2}] unknown BOM"</span>);<a name="568" href="#568">568</a> <a name="569" href="#569">569</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> MessageFormat HTTP_EX_1 = <strong>new</strong> MessageFormat(<a name="570" href="#570">570</a>             <span class="string">"Invalid encoding, CT-MIME [{0}] CT-Enc [{1}] BOM [{2}] XML guess [{3}] XML prolog [{4}], BOM must be NULL"</span>);<a name="571" href="#571">571</a> <a name="572" href="#572">572</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> MessageFormat HTTP_EX_2 = <strong>new</strong> MessageFormat(<a name="573" href="#573">573</a>             <span class="string">"Invalid encoding, CT-MIME [{0}] CT-Enc [{1}] BOM [{2}] XML guess [{3}] XML prolog [{4}], encoding mismatch"</span>);<a name="574" href="#574">574</a> <a name="575" href="#575">575</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> MessageFormat HTTP_EX_3 = <strong>new</strong> MessageFormat(<a name="576" href="#576">576</a>             <span class="string">"Invalid encoding, CT-MIME [{0}] CT-Enc [{1}] BOM [{2}] XML guess [{3}] XML prolog [{4}], Invalid MIME"</span>);<a name="577" href="#577">577</a> <a name="578" href="#578">578</a> }</pre><hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body></html>

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -