/**
* Searches a string in a file.
*
* @param path file path
* @param search codepoints of search string
* @return success flag
*/
private static boolean filterContent(final String path, final int[] search) {
final int cl = search.length;
if (cl == 0) return true;
try (final TextInput ti = new TextInput(new IOFile(path))) {
final IntList il = new IntList(cl - 1);
int c = 0;
while (true) {
if (!il.isEmpty()) {
if (il.remove(0) == search[c++]) continue;
c = 0;
}
while (true) {
final int cp = ti.read();
if (cp == -1 || !XMLToken.valid(cp)) return false;
final int lc = Token.lc(cp);
if (c > 0) il.add(lc);
if (lc == search[c]) {
if (++c == cl) return true;
} else {
c = 0;
break;
}
}
}
} catch (final IOException ex) {
// file may not be accessible
Util.debug(ex);
return false;
}
}
/**
* Refreshes the view after a file has been saved.
*
* @param root root directory
* @param ctx database context
* @throws InterruptedException interruption
*/
void parse(final IOFile root, final Context ctx) throws InterruptedException {
final long id = ++parseId;
final HashSet<String> parsed = new HashSet<>();
final TreeMap<String, InputInfo> errs = new TreeMap<>();
// collect files to be parsed
final ProjectCache pc = cache(root);
final StringList mods = new StringList(), lmods = new StringList();
for (final String path : pc) {
final IOFile file = new IOFile(path);
if (file.hasSuffix(IO.XQSUFFIXES)) (file.hasSuffix(IO.XQMSUFFIX) ? lmods : mods).add(path);
}
mods.add(lmods);
// parse modules
for (final String path : mods) {
if (id != parseId) throw new InterruptedException();
if (parsed.contains(path)) continue;
final IOFile file = new IOFile(path);
try (final TextInput ti = new TextInput(file)) {
// parse query
try (final QueryContext qc = new QueryContext(ctx)) {
final String input = ti.cache().toString();
final boolean lib = QueryProcessor.isLibrary(input);
qc.parse(input, lib, path, null);
// parsing was successful: remember path
parsed.add(path);
for (final byte[] mod : qc.modParsed) parsed.add(Token.string(mod));
} catch (final QueryException ex) {
// parsing failed: remember path
final InputInfo ii = ex.info();
errs.put(path, ii);
parsed.add(ii.path());
}
} catch (final IOException ex) {
// file may not be accessible
Util.debug(ex);
}
}
errors = errs;
}
/**
* Converts an HTML document to XML.
*
* @param io io reference
* @param opts html options
* @return parser
* @throws IOException I/O exception
*/
private static IO toXML(final IO io, final HtmlOptions opts) throws IOException {
// reader could not be initialized; fall back to XML
if (READER == null) return io;
try {
// tries to extract the encoding from the input
final TextInput ti = new TextInput(io);
String enc = ti.encoding();
final byte[] content = ti.content();
// looks for a charset definition
final byte[] encoding = token("charset=");
int cs = indexOf(content, encoding);
if (cs > 0) {
// extracts the encoding string
cs += encoding.length;
int ce = cs;
final int cl = content.length;
while (++ce < cl && content[ce] > 0x28) ;
enc = string(substring(content, cs, ce));
}
// define input
final InputSource is = new InputSource(new ArrayInput(content));
is.setEncoding(supported(enc) ? normEncoding(enc) : UTF8);
// define output
final StringWriter sw = new StringWriter();
final XMLReader reader = (XMLReader) Reflect.get(READER);
final Object writer = Reflect.get(WRITER, sw);
// set TagSoup options
if (opts.get(HtmlOptions.HTML)) {
reader.setFeature("http://xml.org/sax/features/namespaces", false);
opt("method", "html");
opt("omit-xml-declaration", "yes");
}
if (opts.get(HtmlOptions.NONS))
reader.setFeature("http://xml.org/sax/features/namespaces", false);
if (opts.get(HtmlOptions.OMITXML)) opt("omit-xml-declaration", "yes");
if (opts.get(HtmlOptions.NOBOGONS)) reader.setFeature(FEATURES + "ignore-bogons", true);
if (opts.get(HtmlOptions.NODEFAULTS))
reader.setFeature(FEATURES + "default-attributes", false);
if (opts.get(HtmlOptions.NOCOLONS)) reader.setFeature(FEATURES + "translate-colons", true);
if (opts.get(HtmlOptions.NORESTART)) reader.setFeature(FEATURES + "restart-elements", false);
if (opts.get(HtmlOptions.IGNORABLE))
reader.setFeature(FEATURES + "ignorable-whitespace", true);
if (opts.get(HtmlOptions.EMPTYBOGONS)) reader.setFeature(FEATURES + "bogons-empty", true);
if (opts.get(HtmlOptions.ANY)) reader.setFeature(FEATURES + "bogons-empty", false);
if (opts.get(HtmlOptions.NOROOTBOGONS)) reader.setFeature(FEATURES + "root-bogons", false);
if (opts.get(HtmlOptions.NOCDATA)) reader.setFeature(FEATURES + "cdata-elements", false);
if (opts.get(HtmlOptions.LEXICAL))
reader.setProperty("http://xml.org/sax/properties/lexical-handler", writer);
if (opts.contains(HtmlOptions.METHOD)) opt("method", opts.get(HtmlOptions.METHOD));
if (opts.contains(HtmlOptions.DOCTYPESYS))
opt("doctype-system", opts.get(HtmlOptions.DOCTYPESYS));
if (opts.contains(HtmlOptions.DOCTYPEPUB))
opt("doctype-public", opts.get(HtmlOptions.DOCTYPEPUB));
if (opts.contains(HtmlOptions.ENCODING)) is.setEncoding(opts.get(HtmlOptions.ENCODING));
// end TagSoup options
reader.setContentHandler((ContentHandler) writer);
reader.parse(is);
return new IOContent(token(sw.toString()), io.name());
} catch (final SAXException ex) {
Util.errln(ex);
return io;
}
}
