-/*
- * Copyright (C) 2007-2012 Argeo GmbH
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
package org.argeo.util;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
+import java.io.Reader;
+import java.io.UnsupportedEncodingException;
+import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.Collections;
import java.util.List;
-import org.argeo.util.internal.StreamUtils;
-import org.argeo.util.internal.UtilsException;
-
/**
* Parses a CSV file interpreting the first line as a header. The
* {@link #parse(InputStream)} method and the setters are synchronized so that
/**
* Actually process a parsed line. If
- * {@link #setStrictLineAsLongAsHeader(Boolean)} is true (default) the
- * header and the tokens are guaranteed to have the same size.
+ * {@link #setStrictLineAsLongAsHeader(Boolean)} is true (default) the header
+ * and the tokens are guaranteed to have the same size.
*
- * @param lineNumber
- * the current line number, starts at 1 (the header, if header
- * processing is enabled, the first line otherwise)
- * @param header
- * the read-only header or null if {@link #setNoHeader(Boolean)}
- * is true (default is false)
- * @param tokens
- * the parsed tokens
+ * @param lineNumber the current line number, starts at 1 (the header, if header
+ * processing is enabled, the first line otherwise)
+ * @param header the read-only header or null if
+ * {@link #setNoHeader(Boolean)} is true (default is false)
+ * @param tokens the parsed tokens
*/
- protected abstract void processLine(Integer lineNumber,
- List<String> header, List<String> tokens);
+ protected abstract void processLine(Integer lineNumber, List<String> header, List<String> tokens);
/**
* Parses the CSV file (stream is closed at the end)
+ *
+ * @param in the stream to parse
+ *
+ * @deprecated Use {@link #parse(InputStream, Charset)} instead.
*/
+ @Deprecated
public synchronized void parse(InputStream in) {
- parse(in, null);
+ parse(in, (Charset) null);
}
/**
* Parses the CSV file (stream is closed at the end)
+ *
+ * @param in the stream to parse
+ * @param encoding the encoding to use.
+ *
+ * @deprecated Use {@link #parse(InputStream, Charset)} instead.
*/
+ @Deprecated
public synchronized void parse(InputStream in, String encoding) {
- BufferedReader reader = null;
+ Reader reader;
+ if (encoding == null)
+ reader = new InputStreamReader(in);
+ else
+ try {
+ reader = new InputStreamReader(in, encoding);
+ } catch (UnsupportedEncodingException e) {
+ throw new IllegalArgumentException(e);
+ }
+ parse(reader);
+ }
+
+ /**
+ * Parses the CSV file (stream is closed at the end)
+ *
+ * @param in the stream to parse
+ * @param charset the charset to use
+ */
+ public synchronized void parse(InputStream in, Charset charset) {
+ Reader reader;
+ if (charset == null)
+ reader = new InputStreamReader(in);
+ else
+ reader = new InputStreamReader(in, charset);
+ parse(reader);
+ }
+
+ /**
+ * Parses the CSV file (stream is closed at the end)
+ *
+ * @param reader the reader to use (it will be buffered)
+ */
+ public synchronized void parse(Reader reader) {
Integer lineCount = 0;
- try {
- if (encoding == null)
- reader = new BufferedReader(new InputStreamReader(in));
- else
- reader = new BufferedReader(new InputStreamReader(in, encoding));
+ try (BufferedReader bufferedReader = new BufferedReader(reader)) {
List<String> header = null;
if (!noHeader) {
- String headerStr = reader.readLine();
+ String headerStr = bufferedReader.readLine();
if (headerStr == null)// empty file
return;
lineCount++;
StringBuffer currStr = new StringBuffer("");
Boolean wasInquote = false;
while (parseLine(headerStr, header, currStr, wasInquote)) {
- headerStr = reader.readLine();
+ headerStr = bufferedReader.readLine();
if (headerStr == null)
break;
wasInquote = true;
}
String line = null;
- lines: while ((line = reader.readLine()) != null) {
+ lines: while ((line = bufferedReader.readLine()) != null) {
line = preProcessLine(line);
if (line == null) {
// skip line
StringBuffer currStr = new StringBuffer("");
Boolean wasInquote = false;
sublines: while (parseLine(line, tokens, currStr, wasInquote)) {
- line = reader.readLine();
+ line = bufferedReader.readLine();
if (line == null)
break sublines;
wasInquote = true;
if (tokenSize == 1 && line.trim().equals(""))
continue lines;// empty line
if (headerSize != tokenSize) {
- throw new UtilsException("Token size " + tokenSize
- + " is different from header size "
- + headerSize + " at line " + lineCount
- + ", line: " + line + ", header: " + header
+ throw new IllegalStateException("Token size " + tokenSize + " is different from header size "
+ + headerSize + " at line " + lineCount + ", line: " + line + ", header: " + header
+ ", tokens: " + tokens);
}
}
processLine(lineCount, header, tokens);
}
- } catch (UtilsException e) {
- throw e;
} catch (IOException e) {
- throw new UtilsException("Cannot parse CSV file (line: "
- + lineCount + ")", e);
- } finally {
- StreamUtils.closeQuietly(reader);
+ throw new RuntimeException("Cannot parse CSV file (line: " + lineCount + ")", e);
}
}
/**
- * Called before each (logical) line is processed, giving a change to modify
- * it (typically for cleaning dirty files). To be overridden, return the
- * line unchanged by default. Skip the line if 'null' is returned.
+ * Called before each (logical) line is processed, giving a change to modify it
+ * (typically for cleaning dirty files). To be overridden, return the line
+ * unchanged by default. Skip the line if 'null' is returned.
*/
protected String preProcessLine(String line) {
return line;
*
* @return whether to continue parsing this line
*/
- protected Boolean parseLine(String str, List<String> tokens,
- StringBuffer currStr, Boolean wasInquote) {
- // List<String> tokens = new ArrayList<String>();
-
- // System.out.println("#LINE: " + str);
-
+ protected Boolean parseLine(String str, List<String> tokens, StringBuffer currStr, Boolean wasInquote) {
if (wasInquote)
currStr.append('\n');
char[] arr = str.toCharArray();
boolean inQuote = wasInquote;
- // StringBuffer currStr = new StringBuffer("");
for (int i = 0; i < arr.length; i++) {
char c = arr[i];
if (c == separator) {
if (!inQuote) {
tokens.add(currStr.toString());
- // System.out.println("# TOKEN: " + currStr);
- currStr.delete(0, currStr.length());
+// currStr.delete(0, currStr.length());
+ currStr.setLength(0);
+ currStr.trimToSize();
} else {
// we don't remove separator that are in a quoted substring
// System.out
return strictLineAsLongAsHeader;
}
- public synchronized void setStrictLineAsLongAsHeader(
- Boolean strictLineAsLongAsHeader) {
+ public synchronized void setStrictLineAsLongAsHeader(Boolean strictLineAsLongAsHeader) {
this.strictLineAsLongAsHeader = strictLineAsLongAsHeader;
}
projects / lgpl / argeo-commons.git / blobdiff