Examples with DocType edu.stanford.nlp.process.DocumentPreprocessor.DocType used on opensource projects

Example 1 with DocType

use of edu.stanford.nlp.process.DocumentPreprocessor.DocType in project CoreNLP by stanfordnlp.

the class ParseFiles method parseFiles.

public void parseFiles(String[] args, int argIndex, boolean tokenized, TokenizerFactory<? extends HasWord> tokenizerFactory, String elementDelimiter, String sentenceDelimiter, Function<List<HasWord>, List<HasWord>> escaper, String tagDelimiter) {
    final DocType docType = (elementDelimiter == null) ? DocType.Plain : DocType.XML;
    if (op.testOptions.verbose) {
        if (tokenizerFactory != null)
            pwErr.println("parseFiles: Tokenizer factory is: " + tokenizerFactory);
    }
    final Timing timer = new Timing();
    // Loop over the files
    for (int i = argIndex; i < args.length; i++) {
        final String filename = args[i];
        final DocumentPreprocessor documentPreprocessor;
        if (filename.equals("-")) {
            try {
                documentPreprocessor = new DocumentPreprocessor(IOUtils.readerFromStdin(op.tlpParams.getInputEncoding()), docType);
            } catch (IOException e) {
                throw new RuntimeIOException(e);
            }
        } else {
            documentPreprocessor = new DocumentPreprocessor(filename, docType, op.tlpParams.getInputEncoding());
        }
        // Unused values are null per the main() method invocation below
        // null is the default for these properties
        documentPreprocessor.setSentenceFinalPuncWords(tlp.sentenceFinalPunctuationWords());
        documentPreprocessor.setEscaper(escaper);
        documentPreprocessor.setSentenceDelimiter(sentenceDelimiter);
        documentPreprocessor.setTagDelimiter(tagDelimiter);
        documentPreprocessor.setElementDelimiter(elementDelimiter);
        if (tokenizerFactory == null)
            documentPreprocessor.setTokenizerFactory((tokenized) ? null : tlp.getTokenizerFactory());
        else
            documentPreprocessor.setTokenizerFactory(tokenizerFactory);
        // Setup the output
        PrintWriter pwo = pwOut;
        if (op.testOptions.writeOutputFiles) {
            String normalizedName = filename;
            try {
                // this will exception if not a URL
                new URL(normalizedName);
                normalizedName = normalizedName.replaceAll("/", "_");
            } catch (MalformedURLException e) {
            // It isn't a URL, so silently ignore
            }
            String ext = (op.testOptions.outputFilesExtension == null) ? "stp" : op.testOptions.outputFilesExtension;
            String fname = normalizedName + '.' + ext;
            if (op.testOptions.outputFilesDirectory != null && !op.testOptions.outputFilesDirectory.isEmpty()) {
                String fseparator = System.getProperty("file.separator");
                if (fseparator == null || fseparator.isEmpty()) {
                    fseparator = "/";
                }
                File fnameFile = new File(fname);
                fname = op.testOptions.outputFilesDirectory + fseparator + fnameFile.getName();
            }
            try {
                pwo = op.tlpParams.pw(new FileOutputStream(fname));
            } catch (IOException ioe) {
                throw new RuntimeIOException(ioe);
            }
        }
        treePrint.printHeader(pwo, op.tlpParams.getOutputEncoding());
        pwErr.println("Parsing file: " + filename);
        int num = 0;
        int numProcessed = 0;
        if (op.testOptions.testingThreads != 1) {
            MulticoreWrapper<List<? extends HasWord>, ParserQuery> wrapper = new MulticoreWrapper<>(op.testOptions.testingThreads, new ParsingThreadsafeProcessor(pqFactory, pwErr));
            for (List<HasWord> sentence : documentPreprocessor) {
                num++;
                numSents++;
                int len = sentence.size();
                numWords += len;
                pwErr.println("Parsing [sent. " + num + " len. " + len + "]: " + SentenceUtils.listToString(sentence, true));
                wrapper.put(sentence);
                while (wrapper.peek()) {
                    ParserQuery pq = wrapper.poll();
                    processResults(pq, numProcessed++, pwo);
                }
            }
            wrapper.join();
            while (wrapper.peek()) {
                ParserQuery pq = wrapper.poll();
                processResults(pq, numProcessed++, pwo);
            }
        } else {
            ParserQuery pq = pqFactory.parserQuery();
            for (List<HasWord> sentence : documentPreprocessor) {
                num++;
                numSents++;
                int len = sentence.size();
                numWords += len;
                pwErr.println("Parsing [sent. " + num + " len. " + len + "]: " + SentenceUtils.listToString(sentence, true));
                pq.parseAndReport(sentence, pwErr);
                processResults(pq, numProcessed++, pwo);
            }
        }
        treePrint.printFooter(pwo);
        if (op.testOptions.writeOutputFiles)
            pwo.close();
        pwErr.println("Parsed file: " + filename + " [" + num + " sentences].");
    }
    long millis = timer.stop();
    if (summary) {
        if (pcfgLL != null)
            pcfgLL.display(false, pwErr);
        if (depLL != null)
            depLL.display(false, pwErr);
        if (factLL != null)
            factLL.display(false, pwErr);
    }
    if (saidMemMessage) {
        ParserUtils.printOutOfMemory(pwErr);
    }
    double wordspersec = numWords / (((double) millis) / 1000);
    double sentspersec = numSents / (((double) millis) / 1000);
    // easier way!
    NumberFormat nf = new DecimalFormat("0.00");
    pwErr.println("Parsed " + numWords + " words in " + numSents + " sentences (" + nf.format(wordspersec) + " wds/sec; " + nf.format(sentspersec) + " sents/sec).");
    if (numFallback > 0) {
        pwErr.println("  " + numFallback + " sentences were parsed by fallback to PCFG.");
    }
    if (numUnparsable > 0 || numNoMemory > 0 || numSkipped > 0) {
        pwErr.println("  " + (numUnparsable + numNoMemory + numSkipped) + " sentences were not parsed:");
        if (numUnparsable > 0) {
            pwErr.println("    " + numUnparsable + " were not parsable with non-zero probability.");
        }
        if (numNoMemory > 0) {
            pwErr.println("    " + numNoMemory + " were skipped because of insufficient memory.");
        }
        if (numSkipped > 0) {
            pwErr.println("    " + numSkipped + " were skipped as length 0 or greater than " + op.testOptions.maxLength);
        }
    }
}