/**
* Classe manager des importations massives du moteur d'importExport de silverPeas
*
* @author sdevolder
*/
public class RepositoriesTypeManager {
public static final CharSequenceTranslator ESCAPE_ISO8859_1 =
new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE());
/**
* Méthode métier du moteur d'importExport créant toutes les publications massives définies au
* niveau du fichier d'import xml passé en paramètre au moteur d'importExport.
*
* @param userDetail - contient les informations sur l'utilisateur du moteur d'importExport
* @param repositoriesType - objet mappé par castor contenant toutes les informations de création
* des publications du path défini
* @return un objet ComponentReport contenant les informations de création des publications
* unitaires et nécéssaire au rapport détaillé
*/
public void processImport(
RepositoriesType repositoriesType,
ImportSettings settings,
ImportReportManager reportManager) {
List<RepositoryType> listRep_Type = repositoriesType.getListRepositoryType();
Iterator<RepositoryType> itListRep_Type = listRep_Type.iterator();
AttachmentImportExport attachmentIE = new AttachmentImportExport();
VersioningImportExport versioningIE = new VersioningImportExport(settings.getUser());
PdcImportExport pdcIE = new PdcImportExport();
while (itListRep_Type.hasNext()) {
RepositoryType rep_Type = itListRep_Type.next();
String componentId = rep_Type.getComponentId();
int topicId = rep_Type.getTopicId();
String sPath = rep_Type.getPath();
// Création du rapport de repository
MassiveReport massiveReport = new MassiveReport();
reportManager.addMassiveReport(massiveReport, componentId);
massiveReport.setRepositoryPath(sPath);
ComponentInst componentInst =
OrganisationControllerFactory.getOrganisationController().getComponentInst(componentId);
if (componentInst == null) {
// le composant n'existe pas
massiveReport.setError(UnitReport.ERROR_NOT_EXISTS_COMPONENT);
} else {
reportManager.setComponentName(componentId, componentInst.getLabel());
File path = new File(sPath);
if (!path.isDirectory()) {
// La variable path ne peut contenir qu'un dossier
massiveReport.setError(UnitReport.ERROR_NOT_EXISTS_OR_INACCESSIBLE_DIRECTORY);
} else {
GEDImportExport gedIE =
ImportExportFactory.createGEDImportExport(settings.getUser(), componentId);
Iterator<File> itListcontenuPath = getPathContent(path);
while (itListcontenuPath.hasNext()) {
File file = itListcontenuPath.next();
if (file.isFile()) {
settings.setFolderId(String.valueOf(topicId));
importFile(file, reportManager, massiveReport, gedIE, pdcIE, settings);
} else if (file.isDirectory()) {
switch (rep_Type.getMassiveTypeInt()) {
case RepositoryType.NO_RECURSIVE:
// on ne fait rien
break;
case RepositoryType.RECURSIVE_NOREPLICATE:
// traitement récursif spécifique
settings.setPathToImport(file.getAbsolutePath());
processImportRecursiveNoReplicate(
reportManager,
massiveReport,
gedIE,
attachmentIE,
versioningIE,
pdcIE,
settings);
break;
case RepositoryType.RECURSIVE_REPLICATE:
try {
NodeDetail nodeDetail = gedIE.addSubTopicToTopic(file, topicId, massiveReport);
// Traitement récursif spécifique
settings.setPathToImport(file.getAbsolutePath());
settings.setFolderId(nodeDetail.getNodePK().getId());
processImportRecursiveReplicate(
reportManager, massiveReport, gedIE, pdcIE, settings);
} catch (ImportExportException ex) {
massiveReport.setError(UnitReport.ERROR_NOT_EXISTS_OR_INACCESSIBLE_DIRECTORY);
}
break;
}
}
}
}
}
}
}
private PublicationDetail importFile(
File file,
ImportReportManager reportManager,
MassiveReport massiveReport,
GEDImportExport gedIE,
PdcImportExport pdcIE,
ImportSettings settings) {
SilverTrace.debug(
"importExport",
"RepositoriesTypeManager.importFile",
"root.MSG_GEN_ENTER_METHOD",
"file = " + file.getName());
String componentId = gedIE.getCurrentComponentId();
UserDetail userDetail = gedIE.getCurentUserDetail();
PublicationDetail pubDetailToCreate = null;
try {
// Création du rapport unitaire
UnitReport unitReport = new UnitReport();
massiveReport.addUnitReport(unitReport);
// Check the file size
ResourceLocator uploadSettings =
new ResourceLocator("org.silverpeas.util.uploads.uploadSettings", "");
long maximumFileSize = uploadSettings.getLong("MaximumFileSize", 10485760);
long fileSize = file.length();
if (fileSize <= 0L) {
unitReport.setError(UnitReport.ERROR_NOT_EXISTS_OR_INACCESSIBLE_FILE);
reportManager.addNumberOfFilesNotImported(1);
return pubDetailToCreate;
} else if (fileSize > maximumFileSize) {
unitReport.setError(UnitReport.ERROR_FILE_SIZE_EXCEEDS_LIMIT);
reportManager.addNumberOfFilesNotImported(1);
return pubDetailToCreate;
}
// On récupére les infos nécéssaires à la création de la publication
pubDetailToCreate =
PublicationImportExport.convertFileInfoToPublicationDetail(file, settings);
pubDetailToCreate.setPk(new PublicationPK("unknown", "useless", componentId));
if ((settings.isDraftUsed() && pdcIE.isClassifyingMandatory(componentId))
|| settings.isDraftUsed()) {
pubDetailToCreate.setStatus(PublicationDetail.DRAFT);
pubDetailToCreate.setStatusMustBeChecked(false);
}
SilverTrace.debug(
"importExport",
"RepositoriesTypeManager.importFile",
"root.MSG_GEN_PARAM_VALUE",
"pubDetailToCreate.status = " + pubDetailToCreate.getStatus());
// Création de la publication
pubDetailToCreate =
gedIE.createPublicationForMassiveImport(unitReport, pubDetailToCreate, settings);
unitReport.setLabel(pubDetailToCreate.getPK().getId());
SilverTrace.debug(
"importExport",
"RepositoriesTypeManager.importFile",
"root.MSG_GEN_PARAM_VALUE",
"pubDetailToCreate created");
if (FileUtil.isMail(file.getName())) {
// if imported file is an e-mail, its textual content is saved in a dedicated form
// and attached files are attached to newly created publication
processMailContent(
pubDetailToCreate, file, reportManager, unitReport, gedIE, settings.isVersioningUsed());
}
// add attachment
SimpleDocument document;
SimpleDocumentPK pk = new SimpleDocumentPK(null, componentId);
if (settings.isVersioningUsed()) {
document = new HistorisedDocument();
document.setPublicDocument(
settings.getVersionType() == DocumentVersion.TYPE_PUBLIC_VERSION);
} else {
document = new SimpleDocument();
}
document.setPK(pk);
document.setFile(new SimpleAttachment());
document.setFilename(file.getName());
document.setSize(fileSize);
document.getFile().setCreatedBy(userDetail.getId());
if (settings.useFileDates()) {
document.setCreated(pubDetailToCreate.getCreationDate());
if (pubDetailToCreate.getUpdateDate() != null) {
document.setUpdated(pubDetailToCreate.getUpdateDate());
}
} else {
document.setCreated(new Date());
}
document.setForeignId(pubDetailToCreate.getPK().getId());
document.setContentType(FileUtil.getMimeType(file.getName()));
AttachmentServiceFactory.getAttachmentService()
.createAttachment(document, file, pubDetailToCreate.isIndexable(), false);
reportManager.addNumberOfFilesProcessed(1);
reportManager.addImportedFileSize(document.getSize(), componentId);
} catch (Exception ex) {
massiveReport.setError(UnitReport.ERROR_ERROR);
SilverTrace.error(
"importExport", "RepositoriesTypeManager.importFile", "root.EX_NO_MESSAGE", ex);
}
return pubDetailToCreate;
}
private void processMailContent(
PublicationDetail pubDetail,
File file,
ImportReportManager reportManager,
UnitReport unitReport,
GEDImportExport gedIE,
boolean isVersioningUsed)
throws ImportExportException {
String componentId = gedIE.getCurrentComponentId();
UserDetail userDetail = gedIE.getCurentUserDetail();
MailExtractor extractor = null;
Mail mail = null;
try {
extractor = Extractor.getExtractor(file);
mail = extractor.getMail();
} catch (Exception e) {
SilverTrace.error(
"importExport",
"RepositoriesTypeManager.processMailContent",
"importExport.EX_CANT_EXTRACT_MAIL_DATA",
e);
}
if (mail != null) {
// save mail data into dedicated form
String content = mail.getBody();
PublicationContentType pubContent = new PublicationContentType();
XMLModelContentType modelContent = new XMLModelContentType("mail");
pubContent.setXMLModelContentType(modelContent);
List<XMLField> fields = new ArrayList<XMLField>();
modelContent.setFields(fields);
XMLField subject = new XMLField("subject", mail.getSubject());
fields.add(subject);
XMLField body = new XMLField("body", ESCAPE_ISO8859_1.translate(content));
fields.add(body);
XMLField date = new XMLField("date", DateUtil.getOutputDateAndHour(mail.getDate(), "fr"));
fields.add(date);
InternetAddress address = mail.getFrom();
String from = "";
if (StringUtil.isDefined(address.getPersonal())) {
from += address.getPersonal() + " - ";
}
from += "<a href=\"mailto:" + address.getAddress() + "\">" + address.getAddress() + "</a>";
XMLField fieldFROM = new XMLField("from", from);
fields.add(fieldFROM);
Address[] recipients = mail.getAllRecipients();
String to = "";
for (Address recipient : recipients) {
InternetAddress ia = (InternetAddress) recipient;
if (StringUtil.isDefined(ia.getPersonal())) {
to += ia.getPersonal() + " - ";
}
to += "<a href=\"mailto:" + ia.getAddress() + "\">" + ia.getAddress() + "</a></br>";
}
XMLField fieldTO = new XMLField("to", to);
fields.add(fieldTO);
// save form
gedIE.createPublicationContent(
reportManager,
unitReport,
Integer.parseInt(pubDetail.getPK().getId()),
pubContent,
userDetail.getId(),
null);
// extract each file from mail...
try {
List<AttachmentDetail> documents = new ArrayList<AttachmentDetail>();
List<MailAttachment> attachments = extractor.getAttachments();
for (MailAttachment attachment : attachments) {
if (attachment != null) {
AttachmentDetail attDetail = new AttachmentDetail();
AttachmentPK pk = new AttachmentPK("unknown", "useless", componentId);
attDetail.setLogicalName(attachment.getName());
attDetail.setPhysicalName(attachment.getPath());
attDetail.setAuthor(userDetail.getId());
attDetail.setSize(attachment.getSize());
attDetail.setPK(pk);
documents.add(attDetail);
}
}
// ... and save it
if (isVersioningUsed) {
// versioning mode
VersioningImportExport versioningIE = new VersioningImportExport(userDetail);
versioningIE.importDocuments(
pubDetail.getPK().getId(),
componentId,
documents,
Integer.parseInt(userDetail.getId()),
pubDetail.isIndexable());
} else {
// classic mode
AttachmentImportExport attachmentIE = new AttachmentImportExport();
attachmentIE.importAttachments(
pubDetail.getPK().getId(),
componentId,
documents,
userDetail.getId(),
pubDetail.isIndexable());
}
} catch (Exception e) {
SilverTrace.error(
"importExport", "RepositoriesTypeManager.processMailContent", "root.EX_NO_MESSAGE", e);
}
}
}
/**
* Méthode récursive appelée dans le cas de l'importation massive récursive sans création de
* nouveau topic: toutes les publications crées le seront dans le thème passé en paramètre.
*
* @param massiveReport - référence sur l'objet de rapport détaillé du cas import massif
* permettant de le compléter quelque soit le niveau de récursivité.
* @param userDetail - contient les informations sur l'utilisateur du moteur d'importExport.
* @param path - dossier correspondant au niveau de récursivité auquel on se trouve.
* @param componentId - id du composant dans le lequel l'import massif est effectué.
* @param topicId - id du thème dans lequel seront crées les éléments, l'id passé est toujours le
* même dans le cas présent
* @throws ImportExportException
*/
public void processImportRecursiveNoReplicate(
ImportReportManager reportManager,
MassiveReport massiveReport,
GEDImportExport gedIE,
AttachmentImportExport attachmentIE,
VersioningImportExport versioningIE,
PdcImportExport pdcIE,
ImportSettings settings) {
Iterator<File> itListcontenuPath = getPathContent(new File(settings.getPathToImport()));
while (itListcontenuPath.hasNext()) {
File file = itListcontenuPath.next();
if (file.isFile()) {
importFile(file, reportManager, massiveReport, gedIE, pdcIE, settings);
} else if (file.isDirectory()) {
// traitement récursif spécifique
settings.setPathToImport(file.getAbsolutePath());
processImportRecursiveNoReplicate(
reportManager, massiveReport, gedIE, attachmentIE, versioningIE, pdcIE, settings);
}
}
}
/**
* Méthode récursive appelée dans le cas de l'importation massive récursive avec création de
* nouveau topic: chaque sous dossier entrainera la création d'un topic de même nom.
*
* @param massiveReport - référence sur l'objet de rapport détaillé du cas import massif
* permettant de le compléter quelque soit le niveau de récursivité.
* @param userDetail - contient les informations sur l'utilisateur du moteur d'importExport.
* @param path - dossier correspondant au niveau de récursivité auquel on se trouve.
* @param componentId - id du composant dans le lequel l'import massif est effectué.
* @param topicId - id du thème dans lequel seront crées les éléments du niveau de récursivité
* auquel on se trouve.
* @return the list of publications created by the import.
* @throws ImportExportException
*/
public List<PublicationDetail> processImportRecursiveReplicate(
ImportReportManager reportManager,
MassiveReport massiveReport,
GEDImportExport gedIE,
PdcImportExport pdcIE,
ImportSettings settings)
throws ImportExportException {
List<PublicationDetail> publications = new ArrayList<PublicationDetail>();
File path = new File(settings.getPathToImport());
Iterator<File> itListcontenuPath = getPathContent(path);
while (itListcontenuPath.hasNext()) {
File file = itListcontenuPath.next();
if (file.isFile()) {
PublicationDetail publication =
importFile(file, reportManager, massiveReport, gedIE, pdcIE, settings);
if (publication != null) {
publications.add(publication);
}
} else if (file.isDirectory()) {
NodeDetail nodeDetail =
gedIE.addSubTopicToTopic(file, Integer.valueOf(settings.getFolderId()), massiveReport);
// massiveReport.addOneTopicCreated();
// Traitement récursif spécifique
ImportSettings recursiveSettings = settings.clone();
recursiveSettings.setPathToImport(file.getAbsolutePath());
recursiveSettings.setFolderId(nodeDetail.getNodePK().getId());
publications.addAll(
processImportRecursiveReplicate(
reportManager, massiveReport, gedIE, pdcIE, recursiveSettings));
}
}
return publications;
}
private Iterator<File> getPathContent(File path) {
SilverTrace.debug(
"importExport",
"RepositoriesTypeManager.getPathContent",
"root.MSG_GEN_ENTER_METHOD",
"path = " + path.getPath());
// Récupération du contenu du dossier
String[] listContenuStringPath = path.list();
// Tri alphabétique du contenu
Arrays.sort(listContenuStringPath);
List<File> listcontenuPath = convertListStringToListFile(listContenuStringPath, path.getPath());
return listcontenuPath.iterator();
}
/**
* Transforme la table des chaines de caractères de nom de fichier en une liste de fichiers pour
* le chemin passé en paramètre
*
* @param listFileName - table des nom de fichier sous forme de chaine de caractères.
* @param path - chemin des fichiers contenu dans les chaines de caractères.
* @return renvoie une liste d'objets File pour les noms de fichiers passés en paramètres
*/
private List<File> convertListStringToListFile(String[] listFileName, String path) {
List<File> listFile = new ArrayList<File>();
if (listFileName == null) {
return null;
}
for (String aListFileName : listFileName) {
listFile.add(new File(path + File.separator + aListFileName));
}
return listFile;
}
}
/**
* Escapes and unescapes {@code String}s for Java, Java Script, HTML and XML.
*
* <p>#ThreadSafe#
*
* @since 2.0
* @version $Id$
*/
public class StringEscapeUtils {
/* ESCAPE TRANSLATORS */
/**
* Translator object for escaping Java.
*
* <p>While {@link #escapeJava(String)} is the expected method of use, this object allows the Java
* escaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator ESCAPE_JAVA =
new LookupTranslator(
new String[][] {
{"\"", "\\\""},
{"\\", "\\\\"},
})
.with(new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE()))
.with(JavaUnicodeEscaper.outsideOf(32, 0x7f));
/**
* Translator object for escaping EcmaScript/JavaScript.
*
* <p>While {@link #escapeEcmaScript(String)} is the expected method of use, this object allows
* the EcmaScript escaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator ESCAPE_ECMASCRIPT =
new AggregateTranslator(
new LookupTranslator(
new String[][] {
{"'", "\\'"},
{"\"", "\\\""},
{"\\", "\\\\"},
{"/", "\\/"}
}),
new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE()),
JavaUnicodeEscaper.outsideOf(32, 0x7f));
/**
* Translator object for escaping Json.
*
* <p>While {@link #escapeJson(String)} is the expected method of use, this object allows the Json
* escaping functionality to be used as the foundation for a custom translator.
*
* @since 3.2
*/
public static final CharSequenceTranslator ESCAPE_JSON =
new AggregateTranslator(
new LookupTranslator(
new String[][] {
{"\"", "\\\""},
{"\\", "\\\\"},
{"/", "\\/"}
}),
new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_ESCAPE()),
JavaUnicodeEscaper.outsideOf(32, 0x7f));
/**
* Translator object for escaping XML.
*
* <p>While {@link #escapeXml(String)} is the expected method of use, this object allows the XML
* escaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator ESCAPE_XML =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
new LookupTranslator(EntityArrays.APOS_ESCAPE()));
/**
* Translator object for escaping HTML version 3.0.
*
* <p>While {@link #escapeHtml3(String)} is the expected method of use, this object allows the
* HTML escaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator ESCAPE_HTML3 =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE()));
/**
* Translator object for escaping HTML version 4.0.
*
* <p>While {@link #escapeHtml4(String)} is the expected method of use, this object allows the
* HTML escaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator ESCAPE_HTML4 =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_ESCAPE()),
new LookupTranslator(EntityArrays.ISO8859_1_ESCAPE()),
new LookupTranslator(EntityArrays.HTML40_EXTENDED_ESCAPE()));
/**
* Translator object for escaping individual Comma Separated Values.
*
* <p>While {@link #escapeCsv(String)} is the expected method of use, this object allows the CSV
* escaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator ESCAPE_CSV = new CsvEscaper();
// TODO: Create a parent class - 'SinglePassTranslator' ?
// It would handle the index checking + length returning,
// and could also have an optimization check method.
static class CsvEscaper extends CharSequenceTranslator {
private static final char CSV_DELIMITER = ',';
private static final char CSV_QUOTE = '"';
private static final String CSV_QUOTE_STR = String.valueOf(CSV_QUOTE);
private static final char[] CSV_SEARCH_CHARS =
new char[] {CSV_DELIMITER, CSV_QUOTE, CharUtils.CR, CharUtils.LF};
@Override
public int translate(final CharSequence input, final int index, final Writer out)
throws IOException {
if (index != 0) {
throw new IllegalStateException("CsvEscaper should never reach the [1] index");
}
if (StringUtils.containsNone(input.toString(), CSV_SEARCH_CHARS)) {
out.write(input.toString());
} else {
out.write(CSV_QUOTE);
out.write(
StringUtils.replace(input.toString(), CSV_QUOTE_STR, CSV_QUOTE_STR + CSV_QUOTE_STR));
out.write(CSV_QUOTE);
}
return input.length();
}
}
/* UNESCAPE TRANSLATORS */
/**
* Translator object for unescaping escaped Java.
*
* <p>While {@link #unescapeJava(String)} is the expected method of use, this object allows the
* Java unescaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
// TODO: throw "illegal character: \92" as an Exception if a \ on the end of the Java (as per the
// compiler)?
public static final CharSequenceTranslator UNESCAPE_JAVA =
new AggregateTranslator(
new OctalUnescaper(), // .between('\1', '\377'),
new UnicodeUnescaper(),
new LookupTranslator(EntityArrays.JAVA_CTRL_CHARS_UNESCAPE()),
new LookupTranslator(
new String[][] {
{"\\\\", "\\"},
{"\\\"", "\""},
{"\\'", "'"},
{"\\", ""}
}));
/**
* Translator object for unescaping escaped EcmaScript.
*
* <p>While {@link #unescapeEcmaScript(String)} is the expected method of use, this object allows
* the EcmaScript unescaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator UNESCAPE_ECMASCRIPT = UNESCAPE_JAVA;
/**
* Translator object for unescaping escaped Json.
*
* <p>While {@link #unescapeJson(String)} is the expected method of use, this object allows the
* Json unescaping functionality to be used as the foundation for a custom translator.
*
* @since 3.2
*/
public static final CharSequenceTranslator UNESCAPE_JSON = UNESCAPE_JAVA;
/**
* Translator object for unescaping escaped HTML 3.0.
*
* <p>While {@link #unescapeHtml3(String)} is the expected method of use, this object allows the
* HTML unescaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator UNESCAPE_HTML3 =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE()),
new NumericEntityUnescaper());
/**
* Translator object for unescaping escaped HTML 4.0.
*
* <p>While {@link #unescapeHtml4(String)} is the expected method of use, this object allows the
* HTML unescaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator UNESCAPE_HTML4 =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
new LookupTranslator(EntityArrays.ISO8859_1_UNESCAPE()),
new LookupTranslator(EntityArrays.HTML40_EXTENDED_UNESCAPE()),
new NumericEntityUnescaper());
/**
* Translator object for unescaping escaped XML.
*
* <p>While {@link #unescapeXml(String)} is the expected method of use, this object allows the XML
* unescaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator UNESCAPE_XML =
new AggregateTranslator(
new LookupTranslator(EntityArrays.BASIC_UNESCAPE()),
new LookupTranslator(EntityArrays.APOS_UNESCAPE()),
new NumericEntityUnescaper());
/**
* Translator object for unescaping escaped Comma Separated Value entries.
*
* <p>While {@link #unescapeCsv(String)} is the expected method of use, this object allows the CSV
* unescaping functionality to be used as the foundation for a custom translator.
*
* @since 3.0
*/
public static final CharSequenceTranslator UNESCAPE_CSV = new CsvUnescaper();
static class CsvUnescaper extends CharSequenceTranslator {
private static final char CSV_DELIMITER = ',';
private static final char CSV_QUOTE = '"';
private static final String CSV_QUOTE_STR = String.valueOf(CSV_QUOTE);
private static final char[] CSV_SEARCH_CHARS =
new char[] {CSV_DELIMITER, CSV_QUOTE, CharUtils.CR, CharUtils.LF};
@Override
public int translate(final CharSequence input, final int index, final Writer out)
throws IOException {
if (index != 0) {
throw new IllegalStateException("CsvUnescaper should never reach the [1] index");
}
if (input.charAt(0) != CSV_QUOTE || input.charAt(input.length() - 1) != CSV_QUOTE) {
out.write(input.toString());
return input.length();
}
// strip quotes
final String quoteless = input.subSequence(1, input.length() - 1).toString();
if (StringUtils.containsAny(quoteless, CSV_SEARCH_CHARS)) {
// deal with escaped quotes; ie) ""
out.write(StringUtils.replace(quoteless, CSV_QUOTE_STR + CSV_QUOTE_STR, CSV_QUOTE_STR));
} else {
out.write(input.toString());
}
return input.length();
}
}
/* Helper functions */
/**
* {@code StringEscapeUtils} instances should NOT be constructed in standard programming.
*
* <p>Instead, the class should be used as:
*
* <pre>StringEscapeUtils.escapeJava("foo");</pre>
*
* <p>This constructor is public to permit tools that require a JavaBean instance to operate.
*/
public StringEscapeUtils() {
super();
}
// Java and JavaScript
// --------------------------------------------------------------------------
/**
* Escapes the characters in a {@code String} using Java String rules.
*
* <p>Deals correctly with quotes and control-chars (tab, backslash, cr, ff, etc.)
*
* <p>So a tab becomes the characters {@code '\\'} and {@code 't'}.
*
* <p>The only difference between Java strings and JavaScript strings is that in JavaScript, a
* single quote and forward-slash (/) are escaped.
*
* <p>Example:
*
* <pre>
* input string: He didn't say, "Stop!"
* output string: He didn't say, \"Stop!\"
* </pre>
*
* @param input String to escape values in, may be null
* @return String with escaped values, {@code null} if null string input
*/
public static final String escapeJava(final String input) {
return ESCAPE_JAVA.translate(input);
}
/**
* Escapes the characters in a {@code String} using EcmaScript String rules.
*
* <p>Escapes any values it finds into their EcmaScript String form. Deals correctly with quotes
* and control-chars (tab, backslash, cr, ff, etc.)
*
* <p>So a tab becomes the characters {@code '\\'} and {@code 't'}.
*
* <p>The only difference between Java strings and EcmaScript strings is that in EcmaScript, a
* single quote and forward-slash (/) are escaped.
*
* <p>Note that EcmaScript is best known by the JavaScript and ActionScript dialects.
*
* <p>Example:
*
* <pre>
* input string: He didn't say, "Stop!"
* output string: He didn\'t say, \"Stop!\"
* </pre>
*
* @param input String to escape values in, may be null
* @return String with escaped values, {@code null} if null string input
* @since 3.0
*/
public static final String escapeEcmaScript(final String input) {
return ESCAPE_ECMASCRIPT.translate(input);
}
/**
* Escapes the characters in a {@code String} using Json String rules.
*
* <p>Escapes any values it finds into their Json String form. Deals correctly with quotes and
* control-chars (tab, backslash, cr, ff, etc.)
*
* <p>So a tab becomes the characters {@code '\\'} and {@code 't'}.
*
* <p>The only difference between Java strings and Json strings is that in Json, forward-slash (/)
* is escaped.
*
* <p>See http://www.ietf.org/rfc/rfc4627.txt for further details.
*
* <p>Example:
*
* <pre>
* input string: He didn't say, "Stop!"
* output string: He didn't say, \"Stop!\"
* </pre>
*
* @param input String to escape values in, may be null
* @return String with escaped values, {@code null} if null string input
* @since 3.2
*/
public static final String escapeJson(final String input) {
return ESCAPE_JSON.translate(input);
}
/**
* Unescapes any Java literals found in the {@code String}. For example, it will turn a sequence
* of {@code '\'} and {@code 'n'} into a newline character, unless the {@code '\'} is preceded by
* another {@code '\'}.
*
* @param input the {@code String} to unescape, may be null
* @return a new unescaped {@code String}, {@code null} if null string input
*/
public static final String unescapeJava(final String input) {
return UNESCAPE_JAVA.translate(input);
}
/**
* Unescapes any EcmaScript literals found in the {@code String}.
*
* <p>For example, it will turn a sequence of {@code '\'} and {@code 'n'} into a newline
* character, unless the {@code '\'} is preceded by another {@code '\'}.
*
* @see #unescapeJava(String)
* @param input the {@code String} to unescape, may be null
* @return A new unescaped {@code String}, {@code null} if null string input
* @since 3.0
*/
public static final String unescapeEcmaScript(final String input) {
return UNESCAPE_ECMASCRIPT.translate(input);
}
/**
* Unescapes any Json literals found in the {@code String}.
*
* <p>For example, it will turn a sequence of {@code '\'} and {@code 'n'} into a newline
* character, unless the {@code '\'} is preceded by another {@code '\'}.
*
* @see #unescapeJava(String)
* @param input the {@code String} to unescape, may be null
* @return A new unescaped {@code String}, {@code null} if null string input
* @since 3.2
*/
public static final String unescapeJson(final String input) {
return UNESCAPE_JSON.translate(input);
}
// HTML and XML
// --------------------------------------------------------------------------
/**
* Escapes the characters in a {@code String} using HTML entities.
*
* <p>For example:
*
* <p><code>"bread" & "butter"</code> becomes:
*
* <p><code>&quot;bread&quot; &amp; &quot;butter&quot;</code>.
*
* <p>Supports all known HTML 4.0 entities, including funky accents. Note that the commonly used
* apostrophe escape character (&apos;) is not a legal entity and so is not supported).
*
* @param input the {@code String} to escape, may be null
* @return a new escaped {@code String}, {@code null} if null string input
* @see <a href="http://hotwired.lycos.com/webmonkey/reference/special_characters/">ISO
* Entities</a>
* @see <a href="http://www.w3.org/TR/REC-html32#latin1">HTML 3.2 Character Entities for ISO
* Latin-1</a>
* @see <a href="http://www.w3.org/TR/REC-html40/sgml/entities.html">HTML 4.0 Character entity
* references</a>
* @see <a href="http://www.w3.org/TR/html401/charset.html#h-5.3">HTML 4.01 Character
* References</a>
* @see <a href="http://www.w3.org/TR/html401/charset.html#code-position">HTML 4.01 Code
* positions</a>
* @since 3.0
*/
public static final String escapeHtml4(final String input) {
return ESCAPE_HTML4.translate(input);
}
/**
* Escapes the characters in a {@code String} using HTML entities.
*
* <p>Supports only the HTML 3.0 entities.
*
* @param input the {@code String} to escape, may be null
* @return a new escaped {@code String}, {@code null} if null string input
* @since 3.0
*/
public static final String escapeHtml3(final String input) {
return ESCAPE_HTML3.translate(input);
}
// -----------------------------------------------------------------------
/**
* Unescapes a string containing entity escapes to a string containing the actual Unicode
* characters corresponding to the escapes. Supports HTML 4.0 entities.
*
* <p>For example, the string "&lt;Fran&ccedil;ais&gt;" will become
* "<Français>"
*
* <p>If an entity is unrecognized, it is left alone, and inserted verbatim into the result
* string. e.g. "&gt;&zzzz;x" will become ">&zzzz;x".
*
* @param input the {@code String} to unescape, may be null
* @return a new unescaped {@code String}, {@code null} if null string input
* @since 3.0
*/
public static final String unescapeHtml4(final String input) {
return UNESCAPE_HTML4.translate(input);
}
/**
* Unescapes a string containing entity escapes to a string containing the actual Unicode
* characters corresponding to the escapes. Supports only HTML 3.0 entities.
*
* @param input the {@code String} to unescape, may be null
* @return a new unescaped {@code String}, {@code null} if null string input
* @since 3.0
*/
public static final String unescapeHtml3(final String input) {
return UNESCAPE_HTML3.translate(input);
}
// -----------------------------------------------------------------------
/**
* Escapes the characters in a {@code String} using XML entities.
*
* <p>For example: <tt>"bread" & "butter"</tt> => <tt>&quot;bread&quot; &amp;
* &quot;butter&quot;</tt>.
*
* <p>Supports only the five basic XML entities (gt, lt, quot, amp, apos). Does not support DTDs
* or external entities.
*
* <p>Note that Unicode characters greater than 0x7f are as of 3.0, no longer escaped. If you
* still wish this functionality, you can achieve it via the following: {@code
* StringEscapeUtils.ESCAPE_XML.with( NumericEntityEscaper.between(0x7f, Integer.MAX_VALUE) );}
*
* @param input the {@code String} to escape, may be null
* @return a new escaped {@code String}, {@code null} if null string input
* @see #unescapeXml(java.lang.String)
*/
public static final String escapeXml(final String input) {
return ESCAPE_XML.translate(input);
}
// -----------------------------------------------------------------------
/**
* Unescapes a string containing XML entity escapes to a string containing the actual Unicode
* characters corresponding to the escapes.
*
* <p>Supports only the five basic XML entities (gt, lt, quot, amp, apos). Does not support DTDs
* or external entities.
*
* <p>Note that numerical \\u Unicode codes are unescaped to their respective Unicode characters.
* This may change in future releases.
*
* @param input the {@code String} to unescape, may be null
* @return a new unescaped {@code String}, {@code null} if null string input
* @see #escapeXml(String)
*/
public static final String unescapeXml(final String input) {
return UNESCAPE_XML.translate(input);
}
// -----------------------------------------------------------------------
/**
* Returns a {@code String} value for a CSV column enclosed in double quotes, if required.
*
* <p>If the value contains a comma, newline or double quote, then the String value is returned
* enclosed in double quotes.
*
* <p>Any double quote characters in the value are escaped with another double quote.
*
* <p>If the value does not contain a comma, newline or double quote, then the String value is
* returned unchanged. see <a
* href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia</a> and <a
* href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>.
*
* @param input the input CSV column String, may be null
* @return the input String, enclosed in double quotes if the value contains a comma, newline or
* double quote, {@code null} if null string input
* @since 2.4
*/
public static final String escapeCsv(final String input) {
return ESCAPE_CSV.translate(input);
}
/**
* Returns a {@code String} value for an unescaped CSV column.
*
* <p>If the value is enclosed in double quotes, and contains a comma, newline or double quote,
* then quotes are removed.
*
* <p>Any double quote escaped characters (a pair of double quotes) are unescaped to just one
* double quote.
*
* <p>If the value is not enclosed in double quotes, or is and does not contain a comma, newline
* or double quote, then the String value is returned unchanged. see <a
* href="http://en.wikipedia.org/wiki/Comma-separated_values">Wikipedia</a> and <a
* href="http://tools.ietf.org/html/rfc4180">RFC 4180</a>.
*
* @param input the input CSV column String, may be null
* @return the input String, with enclosing double quotes removed and embedded double quotes
* unescaped, {@code null} if null string input
* @since 2.4
*/
public static final String unescapeCsv(final String input) {
return UNESCAPE_CSV.translate(input);
}
}