Skip to content
Snippets Groups Projects
Select Git revision
  • 30f7911a6e9f08ea7e46542a8f3383d7cd5b8f00
  • master default protected
  • djmdev
  • dev
  • cloud_water_contents
  • 1-download-era5
  • sysinstall
  • origin/task/language-editing
  • task/language-editing
  • feature/makefiles
  • v7.1.2
  • v7.1.1
  • v7.1
  • v7.0.4.1
  • 7.0.4
15 results

quick_start.rst

Blame
  • guesslang.py 1018 B
    #!/usr/bin/python3
    
    from guess_language import guess_language
    from argparse import ArgumentParser, FileType
    import sys
    
    __authors__ = ["GG"]
    __date__ = 20191031
    __description__ = 'A simple pdf example'
    
    def guesslang(fnm):
    
      fin= open(fnm, 'rt')
      text= fin.read()
      fin.close()
    
      pages= text.split("\f")
    
      # Note: there should not be anything behind the last Form Feed character
      lastpage= pages.pop()
      # print ('--- [lastpage] ----------------------------------------\n', lastpage)
      lastlang= guess_language(lastpage)
    
      page_num= 1
      for page in pages:
        # print ('--- [page ', page_num, '] ----------------------------------------\n', page)
        lang= guess_language(page)
        print(lang, ' ', page_num, ' ', fnm)
        page_num= page_num+1
    
      if (lastlang != 'UNKNOWN'):
        print(lastlang, ' ', page_num+1, ' ', fnm)
    
    argc= len(sys.argv)
    # print(argc)
    if argc > 1:
      for i in range(1,argc):
        guesslang(sys.argv[i])
    else:
      text= sys.stdin.read()
      lang= guess_language(text)
      print(lang, ' ', 'stdin')