Method ProcessPagesInternal

deps/tesseract/api/baseapi.cpp:1080–1170

In the ideal scenario, Tesseract will start working on data as soon as it can. For example, if you steam a filelist through stdin, we should start the OCR process as soon as the first filename is available. This is particularly useful when hooking Tesseract up to slow hardware such as a book scanning machine. Unfortunately there are tradeoffs. You can't seek on stdin. That makes automatic detecti

// identify the scenario that really matters: filelists on
// stdin. We'll still do our best if the user likes pipes.
bool TessBaseAPI::ProcessPagesInternal(const char* filename,
                                       const char* retry_config,
                                       int timeout_millisec,
                                       TessResultRenderer* renderer) {
  PERF_COUNT_START("ProcessPages")
  bool stdInput = !strcmp(filename, "stdin") || !strcmp(filename, "-");
  if (stdInput) {
#ifdef WIN32
    if (_setmode(_fileno(stdin), _O_BINARY) == -1)
      tprintf("ERROR: cin to binary: %s", strerror(errno));
#endif  // WIN32
  }

  if (stream_filelist) {
    return ProcessPagesFileList(stdin, NULL, retry_config,
                                timeout_millisec, renderer,
                                tesseract_->tessedit_page_number);
  }

  // At this point we are officially in autodection territory.
  // That means any data in stdin must be buffered, to make it
  // seekable.
  std::string buf;
  const l_uint8 *data = NULL;
  if (stdInput) {
    buf.assign((std::istreambuf_iterator<char>(std::cin)),
               (std::istreambuf_iterator<char>()));
    data = reinterpret_cast<const l_uint8 *>(buf.data());
  }

  // Here is our autodetection
  int format;
  int r = (stdInput) ?
      findFileFormatBuffer(data, &format) :
      findFileFormat(filename, &format);

  // Maybe we have a filelist
  if (r != 0 || format == IFF_UNKNOWN) {
    STRING s;
    if (stdInput) {
      s = buf.c_str();
    } else {
      std::ifstream t(filename);
      std::string u((std::istreambuf_iterator<char>(t)),
                    std::istreambuf_iterator<char>());
      s = u.c_str();
    }
    return ProcessPagesFileList(NULL, &s, retry_config,
                                timeout_millisec, renderer,
                                tesseract_->tessedit_page_number);
  }

  // Maybe we have a TIFF which is potentially multipage
  bool tiff = (format == IFF_TIFF || format == IFF_TIFF_PACKBITS ||
               format == IFF_TIFF_RLE || format == IFF_TIFF_G3 ||
               format == IFF_TIFF_G4 || format == IFF_TIFF_LZW ||
               format == IFF_TIFF_ZIP);