public List<Contacts> readContacts(ContactsInitializer contactsInitializer) {
Properties properties;
String pdfinput;
String contents;
String[] content;
String[] contact;
int no_of_pages;
int page_no = ApplicationConstants.TWO;
PdfReader reader = null;
try {
properties = contactsInitializer.getProperties();
pdfinput = properties.getProperty(ApplicationConstants.PDF_INPUT);
reader = new PdfReader(pdfinput);
contents = PdfTextExtractor.getTextFromPage(reader, ApplicationConstants.ONE);
content = contents.split(ApplicationConstants.NEW_LINE, ApplicationConstants.TWO);
contact = content[1].split(ApplicationConstants.NEW_LINE);
genarateContacts(contact);
no_of_pages = reader.getNumberOfPages();
while (page_no <= no_of_pages) {
contents = PdfTextExtractor.getTextFromPage(reader, page_no);
contact = contents.split(ApplicationConstants.NEW_LINE);
genarateContacts(contact);
page_no++;
}
logger.info(list.size() + " contacts added to list from pdf file successfully !");
System.out.println(list.size() + " contacts added to list from pdf file successfully !");
} catch (Exception exception) {
System.out.println("contacts not created !");
logger.error("contacts not created !");
logger.error(exception);
exception.printStackTrace();
} finally {
if (reader != null) {
try {
reader.close();
logger.debug(LoggerConstants.RESOURCES_RELEASED);
} catch (Exception exception) {
logger.error(exception);
exception.printStackTrace();
}
}
}
return list;
}
/**
* Parses a specific area of a PDF to a plain text file.
*
* @param pdf the original PDF
* @param txt the resulting text
* @throws IOException
*/
public void parsePdf(String pdf, String txt) throws IOException {
PdfReader reader = new PdfReader(pdf);
PrintWriter out = new PrintWriter(new FileOutputStream(txt));
Rectangle rect = new Rectangle(70, 80, 490, 580);
RenderFilter filter = new RegionTextRenderFilter(rect);
TextExtractionStrategy strategy;
for (int i = 1; i <= reader.getNumberOfPages(); i++) {
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
out.println(PdfTextExtractor.getTextFromPage(reader, i, strategy));
}
out.flush();
out.close();
}
private void readFile(File file) throws IOException {
FileInputStream inputStream = new FileInputStream(file);
PdfReader reader = new PdfReader(inputStream);
int numberOfPages = reader.getNumberOfPages();
for (int page = 1; page <= numberOfPages; page++) {
String pageContent = PdfTextExtractor.getTextFromPage(reader, page);
List<String> lines = new ArrayList<>(Arrays.asList(pageContent.split("\n")));
for (String line : lines) {
if (line.matches("^\\d{2}\\.\\d{2}\\.\\d{4}.+")) {
parseLine(line);
}
}
}
}
public static void identifySpeakersinTopic(
Map<Integer, Integer> myHalamanStartEnd, Map<Integer, List<String>> myHalamanHash)
throws IOException {
if (myHalamanStartEnd == null || myHalamanHash == null) {
throw new IOException("Missing Pre-req Maps!!");
}
// Itertae though each topic start/end page combination ..
for (Integer current_page : myHalamanStartEnd.keySet()) {
// Need to reinitialize for every new topic; otherwise weirdness ensues :P
Map<String, String> hansard_complete_speakers;
hansard_complete_speakers = new TreeMap<>();
Map<String, String> hansard_unsure_speakers;
hansard_unsure_speakers = new TreeMap<>();
List<Map<String, String>> hansard_complete_logs;
hansard_complete_logs = new ArrayList<>();
List<Map<String, String>> hansard_unsure_logs;
hansard_unsure_logs = new ArrayList<>();
// Get the cleaned up topicbypagenumber .. which is the KEY to the Map
String topicbyPageNumber;
topicbyPageNumber = Utils.getTopicbyPageNumber(current_page, myHalamanHash);
// Above is the main key: TOPIC
// TODO: Below to initialize the 4 subkeyspace: Speakers, Log, Speakers_Maybe, Log_Maybe
// Start iterating through all content ..
int start_page = current_page + 1;
int end_page = myHalamanStartEnd.get(current_page) + 1;
out.println(
"For current block with title: "
+ topicbyPageNumber
+ " start page is "
+ start_page
+ " and end page is "
+ end_page);
for (int i = start_page; i <= end_page; i++) {
out.println("Page " + i);
out.println("===========");
// Ensure pre-reqs of parent folders before proceeding ..
if (Utils.createParentFoldersIfMissing(
String.format(
ITextBlast.working_dir + HansardParser.RESULT_FOLDER,
HansardParser.hansard_filename,
topicbyPageNumber))) {
// Clean the content out of DR headers before next stage in the pipelines ..
String content =
Utils.prepareContentForSpeakerIdentification(
PdfTextExtractor.getTextFromPage(HansardParser.my_reader, i));
// out.println(content);
// Identify people ..
hansard_complete_speakers.putAll(observeSpeakers(content));
Utils.writeMergedSpeakers(
hansard_complete_speakers,
String.format(
ITextBlast.working_dir + RESULT_SPEAKERS,
HansardParser.hansard_filename,
topicbyPageNumber));
// Identify speech block and order them out ..
// put under the growing array for this topic
hansard_complete_logs.addAll(preparePage(content));
Utils.writeMergedSpeechTranscripts(
hansard_complete_logs,
String.format(
ITextBlast.working_dir + RESULT_TRANSCRIPT,
HansardParser.hansard_filename,
topicbyPageNumber));
// extract and write out into JSON log as per Topic
// ... and what they say??
// How to regexp detect paragraph ..
}
// DEBUG: If need to test one topic only; uncomment below ..
// break;
} // End loop for all the pages in the topic
// Like in HansardCopy.java; grab an extra page if necessary
if (!((end_page == 1) || (end_page >= HansardParser.my_reader.getNumberOfPages()))) {
// Put the Maybe here ..
out.println("Page " + (end_page + 1));
out.println("===========");
String content =
Utils.prepareContentForSpeakerIdentification(
PdfTextExtractor.getTextFromPage(HansardParser.my_reader, (end_page + 1)));
// out.println(content);
// Identify people ..
hansard_unsure_speakers.putAll(observeSpeakers(content));
Utils.writeMergedSpeakers(
hansard_unsure_speakers,
String.format(
ITextBlast.working_dir + RESULT_SPEAKERS_UNSURE,
HansardParser.hansard_filename,
topicbyPageNumber));
// Identify speech block and order them out ..
// put under the growing array for this topic
hansard_unsure_logs.addAll(preparePage(content));
Utils.writeMergedSpeechTranscripts(
hansard_unsure_logs,
String.format(
ITextBlast.working_dir + RESULT_TRANSCRIPT_UNSURE,
HansardParser.hansard_filename,
topicbyPageNumber));
}
// DEBUG: First topic only ..
// break;
}
out.println("Final ERR Count: " + HansardParser.my_error_count);
}
