Add words to languagetool suggesting list - java

I use LanguageTool for some spellchecking and spell correction functionality in my application.
The LanguageTool documentation describes how to exclude words from spell checking (with call the addIgnoreTokens(...) method of the spell checking rule you're using).
How do you add some words (e.g., from a specific dictionary) to spell checking? That is, can LanguageTool fix words with misspellings and suggest words from my specific dictionary?

Unfortunately, the API doesn't support this I think. Without the API, you can add words to spelling.txt to get them accepted and used as suggestions. With the API, you might need to extend MorfologikSpellerRule and change this place of the code. (Disclosure: I'm the maintainer of LanguageTool)

I have similar requirement, which is load some custom words into dictionary as "suggest words", not just "ignored words". And finally I extend MorfologikSpellerRule to do this:
Create class MorfologikSpellerRuleEx extends from MorfologikSpellerRule, override the method "match()", and write my own "initSpeller()" for creating spellers.
And then for the language tool, create this custom speller rule to replace existing one.
Code:
Language lang = new AmericanEnglish();
JLanguageTool langTool = new JLanguageTool(lang);
langTool.disableRule("MORFOLOGIK_RULE_EN_US");
try {
MorfologikSpellerRuleEx spellingRule = new MorfologikSpellerRuleEx(JLanguageTool.getMessageBundle(), lang);
spellingRule.setSpellingFilePath(spellingFilePath);
//spellingFilePath is the file has my own words + words from /hunspell/spelling_en-US.txt
langTool.addRule(spellingRule);
} catch (IOException e) {
e.printStackTrace();
}
The code of my custom MorfologikSpellerRuleEx:
public class MorfologikSpellerRuleEx extends MorfologikSpellerRule {
private String spellingFilePath = null;
private boolean ignoreTaggedWords = false;
public MorfologikSpellerRuleEx(ResourceBundle messages, Language language) throws IOException {
super(messages, language);
}
#Override
public String getFileName() {
return "/en/hunspell/en_US.dict";
}
#Override
public String getId() {
return "MORFOLOGIK_SPELLING_RULE_EX";
}
#Override
public void setIgnoreTaggedWords() {
ignoreTaggedWords = true;
}
public String getSpellingFilePath() {
return spellingFilePath;
}
public void setSpellingFilePath(String spellingFilePath) {
this.spellingFilePath = spellingFilePath;
}
private void initSpellerEx(String binaryDict) throws IOException {
String plainTextDict = null;
if (JLanguageTool.getDataBroker().resourceExists(getSpellingFileName())) {
plainTextDict = getSpellingFileName();
}
if (plainTextDict != null) {
BufferedReader br = null;
if (this.spellingFilePath != null) {
try {
br = new BufferedReader(new FileReader(this.spellingFilePath));
}
catch (Exception e) {
br = null;
}
}
if (br != null) {
speller1 = new MorfologikMultiSpeller(binaryDict, br, plainTextDict, 1);
speller2 = new MorfologikMultiSpeller(binaryDict, br, plainTextDict, 2);
speller3 = new MorfologikMultiSpeller(binaryDict, br, plainTextDict, 3);
br.close();
}
else {
speller1 = new MorfologikMultiSpeller(binaryDict, plainTextDict, 1);
speller2 = new MorfologikMultiSpeller(binaryDict, plainTextDict, 2);
speller3 = new MorfologikMultiSpeller(binaryDict, plainTextDict, 3);
}
setConvertsCase(speller1.convertsCase());
} else {
throw new RuntimeException("Could not find ignore spell file in path: " + getSpellingFileName());
}
}
private boolean canBeIgnored(AnalyzedTokenReadings[] tokens, int idx, AnalyzedTokenReadings token)
throws IOException {
return token.isSentenceStart() || token.isImmunized() || token.isIgnoredBySpeller() || isUrl(token.getToken())
|| isEMail(token.getToken()) || (ignoreTaggedWords && token.isTagged()) || ignoreToken(tokens, idx);
}
#Override
public RuleMatch[] match(AnalyzedSentence sentence) throws IOException {
List<RuleMatch> ruleMatches = new ArrayList<>();
AnalyzedTokenReadings[] tokens = getSentenceWithImmunization(sentence).getTokensWithoutWhitespace();
// lazy init
if (speller1 == null) {
String binaryDict = null;
if (JLanguageTool.getDataBroker().resourceExists(getFileName())) {
binaryDict = getFileName();
}
if (binaryDict != null) {
initSpellerEx(binaryDict); //here's the change
} else {
// should not happen, as we only configure this rule (or rather its subclasses)
// when we have the resources:
return toRuleMatchArray(ruleMatches);
}
}
int idx = -1;
for (AnalyzedTokenReadings token : tokens) {
idx++;
if (canBeIgnored(tokens, idx, token)) {
continue;
}
// if we use token.getToken() we'll get ignored characters inside and speller
// will choke
String word = token.getAnalyzedToken(0).getToken();
if (tokenizingPattern() == null) {
ruleMatches.addAll(getRuleMatches(word, token.getStartPos(), sentence));
} else {
int index = 0;
Matcher m = tokenizingPattern().matcher(word);
while (m.find()) {
String match = word.subSequence(index, m.start()).toString();
ruleMatches.addAll(getRuleMatches(match, token.getStartPos() + index, sentence));
index = m.end();
}
if (index == 0) { // tokenizing char not found
ruleMatches.addAll(getRuleMatches(word, token.getStartPos(), sentence));
} else {
ruleMatches.addAll(getRuleMatches(word.subSequence(index, word.length()).toString(),
token.getStartPos() + index, sentence));
}
}
}
return toRuleMatchArray(ruleMatches);
}
}

Related

Execute command line equivalent to Runtime.getRuntime().exec(cmd); in JNI C

I was developing an app which had requirement to implement root detection logic, so by researching I found some detection logic in JAVA and had implemented following class.
class RootDetection {
public boolean isDeviceRooted() {
return checkForBinary("su") || checkForBinary("busybox") || checkForMaliciousPaths() || checkSUonPath()
|| detectRootManagementApps() || detectPotentiallyDangerousApps() || detectRootCloakingApps()
|| checkForDangerousProps() || checkForRWPaths()
|| detectTestKeys() || checkSuExists();
}
private boolean detectTestKeys() {
String buildTags = android.os.Build.TAGS;
String buildFinger = Build.FINGERPRINT;
String product = Build.PRODUCT;
String hardware = Build.HARDWARE;
String display = Build.DISPLAY;
System.out.println("Java: build: " + buildTags + "\nFingerprint: " + buildFinger + "\n Product: " + product + "\n Hardware: " + hardware + "\nDisplay: " + display);
return (buildTags != null) && (buildTags.contains("test-keys") || buildFinger.contains("genric.*test-keys") || product.contains("generic") || product.contains("sdk") || hardware.contains("goldfish") || display.contains(".*test-keys"));
}
private boolean detectRootManagementApps() {
return detectRootManagementApps(null);
}
private boolean detectRootManagementApps(String[] additionalRootManagementApps) {
ArrayList<String> packages = new ArrayList<>();
packages.addAll(Arrays.asList(knownRootAppsPackages));
if (additionalRootManagementApps != null && additionalRootManagementApps.length > 0) {
packages.addAll(Arrays.asList(additionalRootManagementApps));
}
return isAnyPackageFromListInstalled(packages);
}
private boolean detectPotentiallyDangerousApps() {
return detectPotentiallyDangerousApps(null);
}
private boolean detectPotentiallyDangerousApps(String[] additionalDangerousApps) {
ArrayList<String> packages = new ArrayList<>();
packages.addAll(Arrays.asList(knownDangerousAppsPackages));
if (additionalDangerousApps != null && additionalDangerousApps.length > 0) {
packages.addAll(Arrays.asList(additionalDangerousApps));
}
return isAnyPackageFromListInstalled(packages);
}
private boolean detectRootCloakingApps() {
return detectRootCloakingApps(null);
}
private boolean detectRootCloakingApps(String[] additionalRootCloakingApps) {
ArrayList<String> packages = new ArrayList<>();
packages.addAll(Arrays.asList(knownRootCloakingPackages));
if (additionalRootCloakingApps != null && additionalRootCloakingApps.length > 0) {
packages.addAll(Arrays.asList(additionalRootCloakingApps));
}
return isAnyPackageFromListInstalled(packages);
}
private boolean checkForBinary(String filename) {
for (String path : suPaths) {
String completePath = path + filename;
File f = new File(completePath);
boolean fileExists = f.exists();
if (fileExists) {
return true;
}
}
return false;
}
private boolean checkForMaliciousPaths() {
for (String path : maliciousPaths) {
File f = new File(path);
boolean fileExists = f.exists();
if (fileExists) {
return true;
}
}
return false;
}
private static boolean checkSUonPath() {
for (String pathDir : System.getenv("PATH").split(":")) {
if (new File(pathDir, "su").exists()) {
return true;
}
}
return false;
}
private String[] propsReader() {
InputStream inputstream = null;
try {
inputstream = Runtime.getRuntime().exec("getprop").getInputStream();
} catch (IOException e) {
e.printStackTrace();
}
String propval = "";
try {
propval = new Scanner(inputstream).useDelimiter("\\A").next();
} catch (NoSuchElementException e) {
}
return propval.split("\n");
}
private String[] mountReader() {
InputStream inputstream = null;
try {
inputstream = Runtime.getRuntime().exec("mount").getInputStream();
} catch (IOException e) {
e.printStackTrace();
}
if (inputstream == null) return null;
String propval = "";
try {
propval = new Scanner(inputstream).useDelimiter("\\A").next();
} catch (NoSuchElementException e) {
e.printStackTrace();
}
return propval.split("\n");
}
private boolean isAnyPackageFromListInstalled(List<String> packages) {
PackageManager pm = activity.getPackageManager();
for (String packageName : packages) {
try {
pm.getPackageInfo(packageName, 0);
return true;
} catch (PackageManager.NameNotFoundException e) {
}
}
return false;
}
private boolean checkForDangerousProps() {
final Map<String, String> dangerousProps = new HashMap<>();
dangerousProps.put("ro.debuggable", "1");
dangerousProps.put("ro.secure", "0");
String[] lines = propsReader();
for (String line : lines) {
for (String key : dangerousProps.keySet()) {
if (line.contains(key)) {
String badValue = dangerousProps.get(key);
badValue = "[" + badValue + "]";
if (line.contains(badValue)) {
return true;
}
}
}
}
return false;
}
private boolean checkForRWPaths() {
String[] lines = mountReader();
for (String line : lines) {
String[] args = line.split(" ");
if (args.length < 4) {
continue;
}
String mountPoint = args[1];
String mountOptions = args[3];
for (String pathToCheck : pathsThatShouldNotBeWrtiable) {
if (mountPoint.equalsIgnoreCase(pathToCheck)) {
for (String option : mountOptions.split(",")) {
if (option.equalsIgnoreCase("rw")) {
return true;
}
}
}
}
}
return false;
}
private boolean checkSuExists() {
Process process = null;
try {
process = Runtime.getRuntime().exec(new String[]{"which", "su"});
BufferedReader in = new BufferedReader(new InputStreamReader(process.getInputStream()));
return in.readLine() != null;
} catch (Throwable t) {
return false;
} finally {
if (process != null) process.destroy();
}
}
}
but now to increase security I want to do this root detection logic in native C++ JNI code. I managed to migrate package detection code to JNI C but am not able to find anything regarding these 3 functions
checkForDangerousProps(),checkForRWPaths(),checkSuExists()
these 3 use Runtime.getRuntime().exec which am not able to find. can someone help me in converting this 3 logics to JNI C one from above code? Help would be really appreciated.
Pls guys help.

Lucene 6.1 Custom Tokenizer and Analyzer

I'm asking for some help with Lucene 6.1 API.
I tried to extend Lucene's Tokenizer and Analyzer, but I don't understand all guides. In all tutorials, User's Tokenizer overrides the increment. In constructor they have Reader class and in User's Analyzer class they override createComponents method. But in Lucene it has only 1 String argument, so how can I add Reader to my Analyzer?
My code:
public class ChemTokenizer extends Tokenizer{
protected CharTermAttribute charTermAttribute = addAttribute(CharTermAttribute.class);
protected String stringToTokenize;
protected int position = 0;
protected List<int[]> chemicals = new ArrayList<>();
#Override
public boolean incrementToken() throws IOException {
// Clear anything that is already saved in this.charTermAttribute
this.charTermAttribute.setEmpty();
// Get the position of the next symbol
int nextIndex = -1;
Pattern p = Pattern.compile("[^A-zА-я]");
Matcher m = p.matcher(stringToTokenize.substring(position));
nextIndex = m.start();
// Did we lose chemicals?
for (int[] pair: chemicals) {
if (pair[0] < nextIndex && pair[1] > nextIndex) {
//We are in the chemical name
if (position == pair[0]) {
nextIndex = pair[1];
}
else {
nextIndex = pair[0];
}
}
}
// Next separator was found
if (nextIndex != -1) {
String nextToken = stringToTokenize.substring(position, nextIndex);
charTermAttribute.append(nextToken);
position = nextIndex + 1;
return true;
}
// Last part of text
else if (position < stringToTokenize.length()) {
String nextToken = stringToTokenize.substring(position);
charTermAttribute.append(nextToken);
position = stringToTokenize.length();
return true;
}
else {
return false;
}
}
public ChemTokenizer(Reader reader,List<String> additionalKeywords) {
int numChars;
char[] buffer = new char[1024];
StringBuilder stringBuilder = new StringBuilder();
try {
while ((numChars =
reader.read(buffer, 0, buffer.length)) != -1) {
stringBuilder.append(buffer, 0, numChars);
}
}
catch (IOException e) {
throw new RuntimeException(e);
}
stringToTokenize = stringBuilder.toString();
//Checking for keywords
//Doesnt work properly if text has chemical synonyms
for (String keyword: additionalKeywords) {
int[] tmp = new int[2];
//Start of keyword
tmp[0] = stringToTokenize.indexOf(keyword);
tmp[1] = tmp[0] + keyword.length() - 1;
chemicals.add(tmp);
}
}
/* Reset the stored position for this object when reset() is called.
*/
#Override
public void reset() throws IOException {
super.reset();
position = 0;
chemicals = new ArrayList<>();
}
}
And code for Analyzer:
public class ChemAnalyzer extends Analyzer{
List<String> additionalKeywords;
public ChemAnalyzer(List<String> ad) {
additionalKeywords = ad;
}
#Override
protected TokenStreamComponents createComponents(String s, Reader reader) {
Tokenizer tokenizer = new ChemTokenizer(reader,additionalKeywords);
TokenStream filter = new LowerCaseFilter(tokenizer);
return new TokenStreamComponents(tokenizer, filter);
}
}
The problem is that this code doesn't work with Lucene 6
This is what I found in github search, guess you have to create a new tokenizer with out read.
#Override
protected TokenStreamComponents createComponents(String fieldName) {
return new TokenStreamComponents(new WhitespaceTokenizer()); }

how to remove 503 exceptions in java

I have a list of names in the form of a CSV and I am up for google searching those names using java. But the problem that i am facing is that when i initially run the code i am able to search the query but in the middle of the code the code starts to throw 503 exceptions and when i again run the code it starts throwing 503 exceptions from the very beginning.Here is the code that i am using.
public class ExtractInformation
{
static String firstname,middlename,lastname;
public static final int PAGE_NUMBERS = 10;
public static void readCSV()
{
boolean first = true;
try
{
String splitBy = ",";
BufferedReader br = new BufferedReader(new FileReader("E:\\KOLDump\\names.csv"));
String line = null;
String site = null;
while((line=br.readLine())!=null)
{
if(first)
{
first = false;
continue;
}
String[] b = line.split(splitBy);
firstname = b[0];
middlename = b[1];
lastname = b[2];
String name = null;
if(middlename == null || middlename.length() == 0)
{
name = firstname+" "+lastname+" OR "+lastname+" "+firstname.charAt(0);
}
else
{
name = firstname+" "+lastname+" OR "+lastname+" "+firstname.charAt(0)+" OR "+firstname+" "+middlename.charAt(0)+". "+lastname;
}
BufferedReader brs = new BufferedReader(new FileReader("E:\\KOLDump\\site.csv"));
while((site = brs.readLine()) != null)
{
if(first)
{
first = false;
continue;
}
String [] s = site.split(splitBy);
String siteName = s[0];
siteName = (siteName.replace("www.", ""));
siteName = (siteName.replace("http://", ""));
getDataFromGoogle(name.trim(), siteName.trim());
}
brs.close();
}
//br.close();
}
catch(Exception e)
{
System.out.println("unable to read file...some problem in the csv");
}
}
public static void main(String[] args)
{
readCSV();
}
private static void getDataFromGoogle(String query,String siteName)
{
Set<String> result = new HashSet<String>();
String request = "http://www.google.co.in/search?q="+query+" "+siteName;
try
{
Document doc = Jsoup.connect(request).userAgent("Chrome").timeout(10000).get();
Element query_results = doc.getElementById("ires");
Elements gees = query_results.getElementsByClass("g");
for(Element gee : gees)
{
Element h3 = gee.getElementsByTag("h3").get(0);
String annotation = h3.getElementsByTag("a").get(0).attr("href");
if(annotation.split("q=",2)[1].contains(siteName))
{
System.out.println(annotation.split("q=",2)[1]);
}
}
}
catch (IOException e)
{
e.printStackTrace();
}
}
}
any suggestions on how to remove this exceptions from the code would really be helpful.
If you wait a little do the 503's go away? If so, then you're probably being rate-limited by Google. https://support.google.com/gsa/answer/2686272?hl=en
You may need to put some kind of delay between requests.

Getting metadata from SHOUTcast using IcyStreamMeta

I am writing an app for Android that grabs meta data from SHOUTcast mp3 streams. I am using a pretty nifty class I found online that I slightly modified, but I am still having 2 problems.
1) I have to continuously ping the server to update the metadata using a TimerTask. I am not fond of this approach but it was all I could think of.
2) There is a metric tonne of garbage collection while my app is running. Removing the TimerTask got rid of the garbage collection issue so I am not sure if I am just doing it wrong or if this is normal.
Here is the class I am using:
public class IcyStreamMeta {
protected URL streamUrl;
private Map<String, String> metadata;
private boolean isError;
public IcyStreamMeta(URL streamUrl) {
setStreamUrl(streamUrl);
isError = false;
}
/**
* Get artist using stream's title
*
* #return String
* #throws IOException
*/
public String getArtist() throws IOException {
Map<String, String> data = getMetadata();
if (!data.containsKey("StreamTitle"))
return "";
try {
String streamTitle = data.get("StreamTitle");
String title = streamTitle.substring(0, streamTitle.indexOf("-"));
return title.trim();
}catch (StringIndexOutOfBoundsException e) {
return "";
}
}
/**
* Get title using stream's title
*
* #return String
* #throws IOException
*/
public String getTitle() throws IOException {
Map<String, String> data = getMetadata();
if (!data.containsKey("StreamTitle"))
return "";
try {
String streamTitle = data.get("StreamTitle");
String artist = streamTitle.substring(streamTitle.indexOf("-")+1);
return artist.trim();
} catch (StringIndexOutOfBoundsException e) {
return "";
}
}
public Map<String, String> getMetadata() throws IOException {
if (metadata == null) {
refreshMeta();
}
return metadata;
}
public void refreshMeta() throws IOException {
retreiveMetadata();
}
private void retreiveMetadata() throws IOException {
URLConnection con = streamUrl.openConnection();
con.setRequestProperty("Icy-MetaData", "1");
con.setRequestProperty("Connection", "close");
//con.setRequestProperty("Accept", null);
con.connect();
int metaDataOffset = 0;
Map<String, List<String>> headers = con.getHeaderFields();
InputStream stream = con.getInputStream();
if (headers.containsKey("icy-metaint")) {
// Headers are sent via HTTP
metaDataOffset = Integer.parseInt(headers.get("icy-metaint").get(0));
} else {
// Headers are sent within a stream
StringBuilder strHeaders = new StringBuilder();
char c;
while ((c = (char)stream.read()) != -1) {
strHeaders.append(c);
if (strHeaders.length() > 5 && (strHeaders.substring((strHeaders.length() - 4), strHeaders.length()).equals("\r\n\r\n"))) {
// end of headers
break;
}
}
// Match headers to get metadata offset within a stream
Pattern p = Pattern.compile("\\r\\n(icy-metaint):\\s*(.*)\\r\\n");
Matcher m = p.matcher(strHeaders.toString());
if (m.find()) {
metaDataOffset = Integer.parseInt(m.group(2));
}
}
// In case no data was sent
if (metaDataOffset == 0) {
isError = true;
return;
}
// Read metadata
int b;
int count = 0;
int metaDataLength = 4080; // 4080 is the max length
boolean inData = false;
StringBuilder metaData = new StringBuilder();
// Stream position should be either at the beginning or right after headers
while ((b = stream.read()) != -1) {
count++;
// Length of the metadata
if (count == metaDataOffset + 1) {
metaDataLength = b * 16;
}
if (count > metaDataOffset + 1 && count < (metaDataOffset + metaDataLength)) {
inData = true;
} else {
inData = false;
}
if (inData) {
if (b != 0) {
metaData.append((char)b);
}
}
if (count > (metaDataOffset + metaDataLength)) {
break;
}
}
// Set the data
metadata = IcyStreamMeta.parseMetadata(metaData.toString());
// Close
stream.close();
}
public boolean isError() {
return isError;
}
public URL getStreamUrl() {
return streamUrl;
}
public void setStreamUrl(URL streamUrl) {
this.metadata = null;
this.streamUrl = streamUrl;
this.isError = false;
}
public static Map<String, String> parseMetadata(String metaString) {
Map<String, String> metadata = new HashMap<String, String>();
String[] metaParts = metaString.split(";");
Pattern p = Pattern.compile("^([a-zA-Z]+)=\\'([^\\']*)\\'$");
Matcher m;
for (int i = 0; i < metaParts.length; i++) {
m = p.matcher(metaParts[i]);
if (m.find()) {
metadata.put((String)m.group(1), (String)m.group(2));
}
}
return metadata;
}
}
And here is my timer:
private void getMeta() {
timer.schedule(new TimerTask() {
public void run() {
try {
icy = new IcyStreamMeta(new URL(stationUrl));
runOnUiThread(new Runnable() {
public void run() {
try {
artist.setText(icy.getArtist());
title.setText(icy.getTitle());
} catch (IOException e) {
e.printStackTrace();
} catch (StringIndexOutOfBoundsException e) {
e.printStackTrace();
}
}
});
} catch (MalformedURLException e) {
e.printStackTrace();
}
}
},0,5000);
}
Much appreciation for any assistance!
I've replaced the IcyStreamMeta class in my program and am getting the meta data from the 7.html file that is a part of the SHOUTcast spec. Far less data usage and all that so I feel it is a better option.
I am still using the TimerTask, which is acceptable. There is practically no GC any more and I am happy with using 7.html and a little regex. :)

Function based expression message renderer

I'm doing a simple MessageRenderer.
It's specification:
Render message based on an Context (it's a map that's contains all key/value pair parameters)
Supports simple render such as: Your username is << username >>. Assume username in the context is barcelona and the result will be Your username is Barcelona.
Supported function-like object. Example: Current time is << now() >>, now(): is an object that will returns a string of current date time. And result will be: Current time is 2011-05-30
Each parameter of function can also be templated: Current time is << now( << date_format >> ) >> . This template returns a string of current date time with format is the value of key 'date_format' retrieved from the Context. Assume date_format in Context is dd/MM/yyyy and the result will be: Current time is 30/05/2011
Each parameter of function can also be templated with a different method call: Time is << now_locale ( << getLocale() >> ). Assume that getLocale() is an function object that will be return a locale is en_US and the result will be: Time is 2011/05/30 11:20:34 PM
Template can be nested. Example: Your user name is << << username >> >>. It means, Key username has value param1, Key param1 has value is barcelona so the final result will be: Your user name is Barcelona.
My classes and interfaces:
RenderContext.java
public interface RenderContext {
public String getParameter(String key);
}
MessageRenderer.java
public interface MessageRenderer {
public String render(String s, RenderContext... context);
}
MethodExpressionEvaluator.java
// Using this class to implements the method evaluation, such as now(), now_locale()
public interface MethodExpressionEvaluator {
public String evaluate(String[] methodParams, RenderContext... context);
}
AbstractMessageRenderer.java
public abstract class AbstractMessageRenderer implements MessageRenderer {
public static final String DEFAULT_NULL = "###";
public static final String PLACEHOLDER_START_TOKEN = "<<";
public static final String PLACEHOLDER_END_TOKEN = ">>";
protected int lenPlaceholderStartToken = 0;
protected int lenPlaceholderEndToken = 0;
protected String nullToken;
protected String placeholderStartToken;
protected String placeholderEndToken;
protected boolean escape = true;
public AbstractMessageRenderer() {
placeholderStartToken = PLACEHOLDER_START_TOKEN;
placeholderEndToken = PLACEHOLDER_END_TOKEN;
lenPlaceholderStartToken = placeholderStartToken.length();
lenPlaceholderEndToken = placeholderEndToken.length();
nullToken = DEFAULT_NULL;
}
public String getNullToken() {
return nullToken;
}
public void setNullToken(String defaultNull) {
this.nullToken = defaultNull;
}
public String getPlaceholderStartToken() {
return placeholderStartToken;
}
public void setPlaceholderStartToken(String placeholderStartToken) {
this.placeholderStartToken = placeholderStartToken;
lenPlaceholderStartToken = placeholderStartToken.length();
}
public String getPlaceholderEndToken() {
return placeholderEndToken;
}
public void setPlaceholderEndToken(String placeholderEndToken) {
this.placeholderEndToken = placeholderEndToken;
lenPlaceholderEndToken = placeholderEndToken.length();
}
public boolean isEscape() {
return escape;
}
public boolean getEscape() {
return escape;
}
public void setEscape(boolean escape) {
this.escape = escape;
}
public String getParam(String key, RenderContext... context) {
if(context != null)
{
for(RenderContext param:context)
{
if(param != null)
{
String value = param.getParameter(key);
if(!StringUtil.isEmpty(value))
{
return value;
}
}
}
}
return nullToken;
}
public String render(String s, RenderContext... context) {
// handle trivial cases of empty template or no placeholders
if (s == null)
{
Log4j.app.debug("Message is null in template. Cannot render null message.");
return nullToken;
}
if (context == null)
{
Log4j.app.debug("RenderContext is null. Cannot render message with null RenderContext.");
return nullToken;
}
if (s.indexOf(placeholderStartToken) < 0)
{
return s;
}
String msg = nullToken;
try
{
// private int renderTemplate(Renderable r, String src, StringBuffer dst, String nil, int i, String[] marks, StringBuffer end,boolean escapes)
msg = doRender(s, context);
}
catch (Exception e)
{
Log4j.app.error("Exception in rendering template: " + e.getMessage(), e);
return nullToken;
}
return msg;
}
protected abstract String doRender(String s, RenderContext... context);
}
MethodExpressionRenderer.java
public class MethodExpressionRenderer extends AbstractMessageRenderer {
private boolean inSingleQuote = false;
private boolean inDoubleQuote=false;
private int placeholders;
private Stack<String> methodStack;
private String[] endTokens;
private String marker;
private List<String> methodParams;
private String prefix = "&";
public MethodExpressionRenderer() {
super();
methodStack = new Stack<String>();
marker = ",";
endTokens = new String[] { placeholderEndToken, marker, "(", ")" };
methodParams = new ArrayList<String>();
}
public String getPrefix() {
return prefix;
}
public void setPrefix(String prefix) {
this.prefix = prefix;
}
public String getMarker() {
return marker;
}
public void setMarker(String marker) {
this.marker = marker;
endTokens = new String[] { placeholderEndToken, marker };
}
#Override
public void setPlaceholderEndToken(String placeholderEndToken) {
super.setPlaceholderEndToken(placeholderEndToken);
endTokens = new String[] { placeholderEndToken, marker };
}
protected String doRender(String s, RenderContext... context) {
StringBuffer sb = new StringBuffer();
try
{
renderTemplate(s, sb, nullToken, 0, endTokens, null, context);
}
catch (Exception e)
{
Log4j.app.error("Exception in rendering method expression message emplate: " + e.getMessage(), e);
return nullToken;
}
return sb.toString();
}
private int renderTemplate(String src, StringBuffer dst, String nil, int i, String[] marks, StringBuffer end, RenderContext... context) {
int len = src.length();
while (i < len)
{
char c = src.charAt(i);
if (escape)
{
if (c=='\\')
{
i++;
char ch = src.charAt(i);
if(inSingleQuote)
{
if(ch=='\'')
{
inSingleQuote=false;
}
}
else if(inDoubleQuote)
{
if(ch=='"')
{
inDoubleQuote=false;
}
}
else
{
if(ch=='\'')
{
inSingleQuote=true;
}
else if(ch=='"')
{
inDoubleQuote=true;
}
}
dst.append(ch);
i++;
continue;
}
}
if(inSingleQuote)
{
if(c=='\'')
{
inSingleQuote=false;
}
}
else if(inDoubleQuote)
{
if(c=='"')
{
inDoubleQuote=false;
}
}
else
{
if(c=='\'')
{
inSingleQuote=true;
}
else if(c=='"')
{
inDoubleQuote=true;
}
}
// check for end marker
if (marks != null && !inSingleQuote && !inDoubleQuote)
{
for (int m = 0; m < marks.length; m++)
{
// If one of markers found
if (src.regionMatches(i, marks[m], 0, marks[m].length()))
{
// return marker if required
if (end != null)
{
end.append(marks[m]);
}
return i+marks[m].length();
}
}
}
// check for start of placeholder
if (src.regionMatches(i, placeholderStartToken, i, lenPlaceholderStartToken))
{
synchronized(this)
{
++placeholders;
}
i = renderPlaceholder(src, dst, nil, i, new ArrayList<String>(), context);
continue;
}
// just add plain character
if(c != '\'' && c!= '"')
{
dst.append(c);
}
i++;
}
return i;
}
private int renderPlaceholder(String src, StringBuffer dst, String nil, int i, List<String> params, RenderContext... context){
StringBuffer token = new StringBuffer(); // placeholder token
StringBuffer end = new StringBuffer(); // placeholder end marker
String value;
i = renderTemplate(src, token, nil, i+lenPlaceholderStartToken, endTokens, end);
String sToken = token.toString().trim();
String sEnd = end.toString().trim();
boolean isFunction = sEnd.equals("(");
// This is method name
if(isFunction && placeholders > methodStack.size())
{ // Method
synchronized(this)
{
methodStack.push(sToken); // put method into stack
}
}
else if(!isFunction && (methodStack.size()==0) && sEnd.equals(placeholderEndToken)) // Single template param such as <<param>>
{
value = getParam(sToken, context);
if(value != null)
{
if(value.trim().startsWith(placeholderStartToken))
{
value = render(src, context);
}
dst.append(value);
return i;
}
}
// TODO: Process method parameters to invoke
//.... ?????????
// Found end method token ')'
// Pop method out of stack to invoke
if ( (methodStack.size() >0) && (sEnd.length() == 0 || sEnd.equals(")")))
{
String method = null;
synchronized(this)
{
// Pop method out of stack to invoke
method = methodStack.pop();
--placeholders;
dst.append(invokeMethodEvaluator(method, methodParams.toArray(new String[0]), context));
methodParams.clear();
}
}
return i;
}
// Currently this method just implement to test so it just printout the method name
// and its parameter
// We can register MethodExpressionEvaluator to process
protected String invokeMethodEvaluator(String method, String[] params, RenderContext... context){
StringBuffer result = new StringBuffer();
result.append("[ ")
.append(method)
.append(" ( ");
if(params != null)
{
for(int i=0; i<params.length; i++)
{
result.append(params[i]);
if(i != params.length-1)
{
result.append(" , ");
}
}
}
result.append(" ) ")
.append(" ] ");
return result.toString();
}
}
We can easily register more method to the renderer to invoke. Each method will be an object and can be reused. But I'm in trouble how to resolve the nested method parameter. Can anyone give me an advice how we can process nested template of method parameter to invoke??? The line has TODO. Will my code in on the right way???
When you evaluate something like << count( << getTransId() >> ) >> you can either:
perform direct-evaluation as you parse, and push each function onto a stack, so that once you've evaluated getTransId() you pop the stack and use the return value (from the stack) as an argument for count(), or
you can build a parse tree to represent all the function calls that will be made, and then evaluate your parse tree after building it. (Building a tree probably doesn't buy you anything; since you're writing a template engine there is probably no high-level tree operation 'optimizations' that you could perform.)
An excellent little book I really enjoyed was Language Implementation Patterns by Parr. He walks through building simple to complex languages, and covers decisions like this in some depth. (Yes, he uses the ANTLR parser generator throughout, but your code looks like you're familiar enough with hand-generated parsers that different tools won't be a distraction for you.)
I found the bug and fixed it.
This is my new source:
// AbstractMethodExpressionRenderer.java
public class AbstractMethodExpressionRenderer extends AbstractMessageRenderer {
private boolean inSingleQuote = false;
private boolean inDoubleQuote=false;
private Stack<MethodExpressionDescriptor> functionStack;
private String[] endTokens;
private String marker;
private String prefix = "~";
public AbstractMethodExpressionRenderer() {
super();
functionStack = new Stack<MethodExpressionDescriptor>();
marker = ",";
endTokens = new String[] { placeholderEndToken, "(", ")", };
}
private class MethodExpressionDescriptor {
public List<String> params;
public String function;
public MethodExpressionDescriptor() {
params = new ArrayList<String>();
}
public MethodExpressionDescriptor(String name) {
this();
this.function = name;
}
}
public String getPrefix() {
return prefix;
}
public void setPrefix(String prefix) {
this.prefix = prefix;
}
public String getMarker() {
return marker;
}
public void setMarker(String marker) {
this.marker = marker;
endTokens = new String[] { placeholderEndToken, marker };
}
#Override
public void setPlaceholderEndToken(String placeholderEndToken) {
super.setPlaceholderEndToken(placeholderEndToken);
endTokens = new String[] { placeholderEndToken, marker };
}
protected String doRender(String s, RenderContext... context) {
StringBuffer sb = new StringBuffer();
try
{
renderTemplate(s, sb, nullToken, 0, endTokens, null, context);
}
catch (Exception e)
{
Log4j.app.error("Exception in rendering method expression message emplate: " + e.getMessage(), e);
return nullToken;
}
return sb.toString();
}
private int renderTemplate(String src, StringBuffer dst, String nil, int i, String[] marks, StringBuffer end, RenderContext... context) {
int len = src.length();
while (i < len)
{
char c = src.charAt(i);
if (escape)
{
if (c=='\\')
{
i++;
char ch = src.charAt(i);
if(inSingleQuote)
{
if(ch=='\'')
{
inSingleQuote=false;
}
}
else if(inDoubleQuote)
{
if(ch=='"')
{
inDoubleQuote=false;
}
}
else
{
if(ch=='\'')
{
inSingleQuote=true;
}
else if(ch=='"')
{
inDoubleQuote=true;
}
}
dst.append(ch);
i++;
continue;
}
}
if(inSingleQuote)
{
if(c=='\'')
{
inSingleQuote=false;
}
}
else if(inDoubleQuote)
{
if(c=='"')
{
inDoubleQuote=false;
}
}
else
{
if(c=='\'')
{
inSingleQuote=true;
}
else if(c=='"')
{
inDoubleQuote=true;
}
}
// check for end marker
if (marks != null && !inSingleQuote && !inDoubleQuote)
{
for (int m = 0; m < marks.length; m++)
{
// If one of markers found
if (src.regionMatches(i, marks[m], 0, marks[m].length()))
{
// return marker if required
if (end != null)
{
end.append(marks[m]);
}
return i+marks[m].length();
}
}
}
// check for start of placeholder
if (src.regionMatches(i, placeholderStartToken, 0, lenPlaceholderStartToken))
{
i = renderPlaceholder(src, dst, nil, i, new ArrayList<String>(), context);
continue;
}
// just add plain character
if(c != '\'' && c!= '"')
{
dst.append(c);
}
i++;
}
return i;
}
/**
* Render a placeholder as follows:
*
* <<key>>: Simple render, key value map
* <<function(<<param1>>, <<param2>>)>> : Function object render
*
* #param src
* #param dst
* #param nil
* #param i
* #param params
* #param context
* #return
*/
private int renderPlaceholder(String src, StringBuffer dst, String nil, int i, List<String> params, RenderContext... context){
StringBuffer token = new StringBuffer(); // placeholder token
StringBuffer end = new StringBuffer(); // placeholder end marker
String value = null;
// Simple key
i = renderTemplate(src, token, nil, i+lenPlaceholderStartToken, endTokens, end, context);
String sToken = token.toString().trim();
String sEnd = end.toString().trim();
// This is method name
if(sEnd.equals("("))
{ // Method
functionStack.add(new MethodExpressionDescriptor(sToken));
}
else // Try to resolve value
{
if(sToken.startsWith(placeholderStartToken))
{
value = render(sToken, context);
}
else if(sToken.startsWith(prefix))
{
if(functionStack.size() > 0)
{
functionStack.peek().params.add(sToken.substring(1));
}
return i;
}
else
{
value = getParam(sToken, context);
}
}
if (sEnd.length() == 0 || sEnd.equals(placeholderEndToken))
{
// No method found but found the end of placeholder token
if(functionStack.size() == 0)
{
if(value != null)
{
dst.append(value);
}
else
{
dst.append(nil);
}
}
else
{
functionStack.peek().params.add(value);
}
}
else
{
if(value != null)
{
value = value.trim();
}
if(end.substring(0, 1).equals("(") ||
end.substring(0, 1).equals(marker))
{
// right hand side is remainder of placeholder
StringBuffer tmp = new StringBuffer();
end = new StringBuffer();
i = renderTemplate(src, tmp, nil, i, endTokens, end, context);
}
if(end.substring(0, 1).equals(")"))
{
if ( functionStack.size() > 0 )
{
// Pop method out of stack to invoke
MethodExpressionDescriptor descriptor = functionStack.pop();
if(functionStack.size() > 0 )
{
functionStack.peek().params.add(invokeMethodEvaluator(descriptor.function, descriptor.params.toArray(new String[0]), context));
}
else
{
dst.append(invokeMethodEvaluator(descriptor.function, descriptor.params.toArray(new String[0]), context));
}
end = new StringBuffer();
StringBuffer tmp = new StringBuffer();
i = renderTemplate(src, tmp, nil, i, endTokens, end, context);
}
}
}
return i;
}
protected String invokeMethodEvaluator(String method, String[] params, RenderContext... context){
StringBuffer result = new StringBuffer();
result.append("[ ")
.append(method)
.append(" ( ");
if(params != null)
{
for(int i=0; i<params.length; i++)
{
result.append(params[i]);
if(i != params.length-1)
{
result.append(" , ");
}
}
}
result.append(" ) ")
.append(" ] ");
return result.toString();
}
}

Categories

Resources