Rationalize CLI across lrf utilities.

src/libprs500/ebooks/lrf/__init__.py

@@ -115,6 +115,40 @@ def option_parser(usage):
                     help='''Top margin of page. Default is %default px.''')
     page.add_option('--bottom-margin', default=0, dest='bottom_margin', type='int',
                     help='''Bottom margin of page. Default is %default px.''')
+    link = parser.add_option_group('LINK PROCESSING OPTIONS')
+    link.add_option('--link-levels', action='store', type='int', default=sys.maxint, \
+                      dest='link_levels',
+                      help=r'''The maximum number of levels to recursively process '''
+                              '''links. A value of 0 means thats links are not followed. '''
+                              '''A negative value means that <a> tags are ignored.''')
+    link.add_option('--link-exclude', dest='link_exclude', default='$',
+                      help='''A regular expression. <a> tags whoose href '''
+                      '''matches will be ignored. Defaults to %default''')
+    chapter = parser.add_option_group('CHAPTER OPTIONS')
+    chapter.add_option('--disable-chapter-detection', action='store_false', 
+                      default=True, dest='chapter_detection', 
+                      help='''Prevent html2lrf from automatically inserting page breaks'''
+                      ''' before what it thinks are chapters.''')
+    chapter.add_option('--chapter-regex', dest='chapter_regex', 
+                      default='chapter|book|appendix',
+                      help='''The regular expression used to detect chapter titles.'''
+                      ''' It is searched for in heading tags. Defaults to %default''')     
+    chapter.add_option('--page-break-before', dest='page_break', default='h[12]',
+                      help='''If html2lrf does not find any page breaks in the '''
+                      '''html file and cannot detect chapter headings, it will '''
+                      '''automatically insert page-breaks before the tags whose '''
+                      '''names match this regular expression. Defaults to %default. '''
+                      '''You can disable it by setting the regexp to "$". '''
+                      '''The purpose of this option is to try to ensure that '''
+                      '''there are no really long pages as this degrades the page '''
+                      '''turn performance of the LRF. Thus this option is ignored '''
+                      '''if the current page has only a few elements.''')
+    chapter.add_option('--force-page-break-before', dest='force_page_break',
+                       default='$', help='Like --page-break-before, but page breaks are forced.')
+    prepro = parser.add_option_group('PREPROCESSING OPTIONS')
+    prepro.add_option('--baen', action='store_true', default=False, dest='baen',
+                      help='''Preprocess Baen HTML files to improve generated LRF.''')
+
     
     fonts = parser.add_option_group('FONT FAMILIES', 
     '''Specify trutype font families for serif, sans-serif and monospace fonts. '''

src/libprs500/ebooks/lrf/html/convert_from.py

@@ -35,7 +35,7 @@ except ImportError:
 from libprs500.ebooks.BeautifulSoup import BeautifulSoup, BeautifulStoneSoup, \
                 Comment, Tag, NavigableString, Declaration, ProcessingInstruction
 from libprs500.ebooks.lrf.pylrs.pylrs import Paragraph, CR, Italic, ImageStream, \
-                TextBlock, ImageBlock, JumpButton, CharButton, Bold, Space, \
+                TextBlock, ImageBlock, JumpButton, CharButton, Bold,\
                 Plot, Image, BlockSpace, RuledLine, BookSetting, Canvas, DropCaps, \
                 LrsError
 from libprs500.ebooks.lrf.pylrs.pylrs import Span as _Span
@@ -1368,74 +1368,28 @@ def try_opf(path, options):
             print >>sys.stderr, 'Failed to process opf file', err
         pass
                 
-            
+def option_parser():
-def option_parser(parser=None, usage='''Usage: %prog [options] mybook.[html|rar|zip]\n\n'''
+    return lrf_option_parser('''Usage: %prog [options] mybook.[html|rar|zip]\n\n'''
-                    '''%prog converts mybook.html to mybook.lrf'''         
+                    '''%prog converts mybook.html to mybook.lrf''')
-                  ):
-    if not parser:
-        parser = lrf_option_parser(usage)
-    link = parser.add_option_group('LINK PROCESSING OPTIONS')
-    link.add_option('--link-levels', action='store', type='int', default=sys.maxint, \
-                      dest='link_levels',
-                      help=r'''The maximum number of levels to recursively process '''
-                              '''links. A value of 0 means thats links are not followed. '''
-                              '''A negative value means that <a> tags are ignored.''')
-    link.add_option('--link-exclude', dest='link_exclude', default='$',
-                      help='''A regular expression. <a> tags whoose href '''
-                      '''matches will be ignored. Defaults to %default''')
-    chapter = parser.add_option_group('CHAPTER OPTIONS')
-    chapter.add_option('--disable-chapter-detection', action='store_false', 
-                      default=True, dest='chapter_detection', 
-                      help='''Prevent html2lrf from automatically inserting page breaks'''
-                      ''' before what it thinks are chapters.''')
-    chapter.add_option('--chapter-regex', dest='chapter_regex', 
-                      default='chapter|book|appendix',
-                      help='''The regular expression used to detect chapter titles.'''
-                      ''' It is searched for in heading tags. Defaults to %default''')     
-    chapter.add_option('--page-break-before', dest='page_break', default='h[12]',
-                      help='''If html2lrf does not find any page breaks in the '''
-                      '''html file and cannot detect chapter headings, it will '''
-                      '''automatically insert page-breaks before the tags whose '''
-                      '''names match this regular expression. Defaults to %default. '''
-                      '''You can disable it by setting the regexp to "$". '''
-                      '''The purpose of this option is to try to ensure that '''
-                      '''there are no really long pages as this degrades the page '''
-                      '''turn performance of the LRF. Thus this option is ignored '''
-                      '''if the current page has only a few elements.''')
-    chapter.add_option('--force-page-break-before', dest='force_page_break',
-                       default='$', help='Like --page-break-before, but page breaks are forced.')
-    prepro = parser.add_option_group('PREPROCESSING OPTIONS')
-    prepro.add_option('--baen', action='store_true', default=False, dest='baen',
-                      help='''Preprocess Baen HTML files to improve generated LRF.''')
-    return parser
 
-
+def main(args=sys.argv):
-
-def parse_options(argv=sys.argv[1:], cli=True, parser=None):
-    """ CLI for html -> lrf conversions """
-    parser = option_parser(parser)
-    options, args = parser.parse_args(args=argv)
-    
-    if len(args) != 1:
-        if cli:
-            parser.print_help()
-        raise ConversionError, 'no filename specified'
-    if options.output:
-        options.output = os.path.abspath(os.path.expanduser(options.output))    
-    return options, args, parser
-
-
-def main():    
     try:
-        options, args, parser = parse_options()
+        parser = option_parser()
-        src = args[0]
+        options, args = parser.parse_args(args)    
+        if options.output:
+            options.output = os.path.abspath(os.path.expanduser(options.output))
+        if len(args) != 2:
+            parser.print_help()
+            return 1
+        src = args[1]
         if options.verbose:
             import warnings
             warnings.defaultaction = 'error'
     except Exception, err:
         print >> sys.stderr, err
-        sys.exit(1)    
+        return 1    
     process_file(src, options)
+    return 0
 
 def console_query(dirpath, candidate, docs):
     if len(docs) == 1:
@@ -1500,4 +1454,4 @@ def get_path(path, query=console_query):
 
 
 if __name__ == '__main__':
-    main()
+    sys.exit(main())

src/libprs500/ebooks/lrf/lit/convert_from.py

@@ -15,29 +15,19 @@
 import os, sys, shutil, glob
 from tempfile import mkdtemp
 from subprocess import Popen, PIPE
-from libprs500.ebooks.lrf import option_parser
+from libprs500.ebooks.lrf import option_parser as lrf_option_parser
 from libprs500.ebooks import ConversionError
-from libprs500.ebooks.lrf.html.convert_from import parse_options as html_parse_options
 from libprs500.ebooks.lrf.html.convert_from import process_file
 from libprs500 import isosx
 CLIT = 'clit'
 if isosx and hasattr(sys, 'frameworks_dir'):
     CLIT = os.path.join(sys.frameworks_dir, CLIT)
 
-def parse_options(cli=True):
+def option_parser():
-    """ CLI for lit -> lrf conversions """
+    return lrf_option_parser(
-    parser = option_parser(
+        '''Usage: %prog [options] mybook.lit\n\n'''
-        """usage: %prog [options] mybook.lit
+        '''%prog converts mybook.lit to mybook.lrf'''
-        
-        %prog converts mybook.lit to mybook.lrf
-        """
         )
-    options, args = parser.parse_args()
-    if len(args) != 1:
-        if cli:
-            parser.print_help()
-        raise ConversionError, 'no filename specified'
-    return options, args, parser
 
 def generate_html(pathtolit):
     if not os.access(pathtolit, os.R_OK):
@@ -52,56 +42,40 @@ def generate_html(pathtolit):
         raise ConversionError, err
     return tdir
 
-def main():
+def main(args=sys.argv):
+    parser = option_parser()
+    options, args = parser.parse_args(args)
+    if len(args) != 2:            
+        parser.print_help()
+        print
+        print 'No lit file specified'
+        return 1
+    lit = os.path.abspath(os.path.expanduser(args[1]))        
+    tdir = generate_html(lit)
     try:
-        options, args, parser = parse_options()
+        l = glob.glob(os.path.join(tdir, '*toc*.htm*'))
-        lit = os.path.abspath(os.path.expanduser(args[0]))        
+        if not l:
-        tdir = generate_html(lit)
+            l = glob.glob(os.path.join(tdir, '*top*.htm*'))
-        try:
+        if not l:
-            l = glob.glob(os.path.join(tdir, '*toc*.htm*'))
+            l = glob.glob(os.path.join(tdir, '*contents*.htm*'))
+        if not l:
+            l = glob.glob(os.path.join(tdir, '*.htm*'))
             if not l:
-                l = glob.glob(os.path.join(tdir, '*top*.htm*'))
+                raise ConversionError, 'Conversion of lit to html failed. Cannot find html file.'
-            if not l:
+            maxsize, htmlfile = 0, None
-                l = glob.glob(os.path.join(tdir, '*contents*.htm*'))
+            for c in l:
-            if not l:
+                sz = os.path.getsize(c)
-                l = glob.glob(os.path.join(tdir, '*.htm*'))
+                if sz > maxsize:
-                if not l:
+                    maxsize, htmlfile = sz, c
-                    raise ConversionError, 'Conversion of lit to html failed. Cannot find html file.'
+        else:
-                maxsize, htmlfile = 0, None
+            htmlfile = l[0]
-                for c in l:
+        if not options.output:
-                    sz = os.path.getsize(c)
+            ext = '.lrs' if options.lrs else '.lrf'
-                    if sz > maxsize:
+            options.output = os.path.basename(os.path.splitext(args[1])[0]) + ext  
-                        maxsize, htmlfile = sz, c
+        process_file(htmlfile, options)         
-            else:
+    finally:
-                htmlfile = l[0]
+        shutil.rmtree(tdir)
-            for i in range(1, len(sys.argv)):
+    
-                if sys.argv[i] == args[0]:
-                    sys.argv.remove(sys.argv[i])
-                    break
-            sys.argv.append(htmlfile)
-            o_spec = False
-            for arg in sys.argv[1:]:
-                arg = arg.lstrip()
-                if arg.startswith('-o') or arg.startswith('--output'):
-                    o_spec = True
-                    break
-            ext = '.lrf'
-            for arg in sys.argv[1:]:
-                if arg.strip() == '--lrs':
-                    ext = '.lrs'
-                    break
-            if not o_spec:
-                sys.argv.append('-o')
-                sys.argv.append(os.path.splitext(os.path.basename(lit))[0]+ext)
-            options, args, parser = html_parse_options(parser=parser)
-            process_file(htmlfile, options)         
-        finally:
-            shutil.rmtree(tdir)
-    except ConversionError, err:
-        print >>sys.stderr, err
-        sys.exit(1)
             
 if __name__ == '__main__':
-    main()
+    sys.exit(main())
-    
-        

src/libprs500/ebooks/lrf/meta.py

@@ -559,19 +559,16 @@ class LRFMetaFile(object):
         self._file.write(val)
         
 
-def parse_options(argv=None, cli=True):
+def option_parser():
     from optparse import OptionParser
-    from libprs500 import __version__ as VERSION
+    from libprs500 import __appname__, __version__
-    if not argv:
-        argv = sys.argv[1:]
     parser = OptionParser(usage = \
-      """%prog [options] mybook.lrf
+      '''%prog [options] mybook.lrf\n\n'''
-      
+      '''Show/edit the metadata in an LRF file.\n\n'''      
-      Show/edit the metadata in an LRF file.
+      '''WARNING: Based on reverse engineering the LRF format.\n''' 
-      
+      '''Making changes may render your LRF file unreadable.''', 
-      WARNING: Based on reverse engineering the LRF format. 
+      version=__appname__+' '+__version__,
-      Making changes may render your LRF file unreadable. 
+      epilog='Created by Kovid Goyal')
-      """, version=VERSION)
     parser.add_option("-t", "--title", action="store", type="string", \
                     dest="title", help="Set the book title")
     parser.add_option('--title-sort', action='store', type='string', default=None,
@@ -594,20 +591,20 @@ def parse_options(argv=None, cli=True):
                     help="Extract thumbnail from LRF file")
     parser.add_option("-p", "--page", action="store", type="string", \
                     dest="page", help="Don't know what this is for")
-    options, args = parser.parse_args(args=argv)
+    
-    if len(args) != 1:
+    return parser
-        if cli:
-            parser.print_help()
-        raise LRFException, 'no filename specified'
-    return options, args, parser
 
-def main():
+
+def main(args=sys.argv):
     import os.path
-    try:
+    parser = option_parser()
-        options, args, parser = parse_options()
+    options, args = parser.parse_args(args)
-    except:
+    if len(args) != 2:
-        sys.exit(1)
+        parser.print_help()
-    lrf = LRFMetaFile(open(args[0], "r+b"))
+        print
+        print 'No lrf file specified'
+        return 1
+    lrf = LRFMetaFile(open(args[1], "r+b"))
     if options.title:
         lrf.title        = options.title
     if options.title_reading != None:
@@ -646,4 +643,4 @@ def main():
         print "Thumbnail:", td
         
 if __name__ == '__main__':
-    main()
+    sys.exit(main())

src/libprs500/ebooks/lrf/rtf/convert_from.py

@@ -14,9 +14,8 @@
 ##    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 import os, sys, tempfile, subprocess, shutil
 
-from libprs500.ebooks.lrf import option_parser
+from libprs500.ebooks.lrf import option_parser as lrf_option_parser
 from libprs500.ebooks.metadata.meta import get_metadata
-from libprs500.ebooks.lrf.html.convert_from import parse_options as html_parse_options
 from libprs500.ebooks.lrf.html.convert_from import process_file
 from libprs500.ebooks import ConversionError
 from libprs500 import isosx
@@ -25,20 +24,11 @@ UNRTF = 'unrtf'
 if isosx and hasattr(sys, 'frameworks_dir'):
     UNRTF = os.path.join(sys.frameworks_dir, UNRTF)
 
-def parse_options(cli=True):
+def option_parser():
-    """ CLI for rtf -> lrf conversions """
+    return lrf_option_parser(
-    parser = option_parser(
+        '''Usage: %prog [options] mybook.rtf\n\n'''
-        """usage: %prog [options] mybook.rtf
+        '''%prog converts mybook.rtf to mybook.lrf'''
-        
-        %prog converts mybook.rtf to mybook.lrf
-        """
         )
-    options, args = parser.parse_args()
-    if len(args) != 1:
-        if cli:
-            parser.print_help()
-        raise ConversionError, 'no filename specified'
-    return options, args, parser
 
 def generate_html(rtfpath):
     tdir = tempfile.mkdtemp(prefix='rtf2lrf_')
@@ -61,58 +51,41 @@ def generate_html(rtfpath):
     finally:
         os.chdir(cwd)
         
-def main():
+def main(args=sys.argv):
+    parser = option_parser()
+    options, args = parser.parse_args(args)
+    if len(args) != 2:
+        parser.print_help()
+        print
+        print 'No rtf file specified'
+        return 1
+    rtf = os.path.abspath(os.path.expanduser(args[1]))
+    f = open(rtf, 'rb')
+    mi = get_metadata(f, 'rtf')
+    f.close()
+    html = generate_html(rtf)
+    tdir = os.path.dirname(html)
     try:
-        options, args, parser = parse_options()
+        if not options.output:
-        rtf = os.path.abspath(os.path.expanduser(args[0]))
+            ext = '.lrs' if options.lrs else '.lrf'
-        f = open(rtf, 'rb')
+            options.output = os.path.basename(os.path.splitext(args[1])[0]) + ext 
-        mi = get_metadata(f, 'rtf')
+        if (not options.title or options.title == 'Unknown') and mi.title:
-        f.close()
+            sys.argv.append('-t')
-        html = generate_html(rtf)
+            sys.argv.append('"'+mi.title+'"')
-        tdir = os.path.dirname(html)
+        if (not options.author or options.author == 'Unknown') and mi.author:
-        try:
+            sys.argv.append('-a')
-            for i in range(len(sys.argv)):
+            sys.argv.append('"'+mi.author+'"')
-                if sys.argv[i] == args[0]:
+        if (not options.category or options.category == 'Unknown') and mi.category:
-                    sys.argv[i] = html
+            sys.argv.append('--category')
-            o_spec = False
+            sys.argv.append('"'+mi.category+'"')
-            for arg in sys.argv[1:]:
+        if (not options.freetext or options.freetext == 'Unknown') and mi.comments:
-                arg = arg.lstrip()
+            sys.argv.append('--comment')
-                if arg.startswith('-o') or arg.startswith('--output'):
+            sys.argv.append('"'+mi.comments+'"')
-                    o_spec = True
+        process_file(html, options)
-                    break
+    finally:
-            ext = '.lrf'
+        shutil.rmtree(tdir)
-            for arg in sys.argv[1:]:
-                if arg.strip() == '--lrs':
-                    ext = '.lrs'
-                    break
-            if not o_spec:
-                sys.argv.append('-o')
-                sys.argv.append(os.path.splitext(os.path.basename(rtf))[0]+ext)
-            
-            if (not options.title or options.title == 'Unknown') and mi.title:
-                sys.argv.append('-t')
-                sys.argv.append('"'+mi.title+'"')
-            if (not options.author or options.author == 'Unknown') and mi.author:
-                sys.argv.append('-a')
-                sys.argv.append('"'+mi.author+'"')
-            if (not options.category or options.category == 'Unknown') and mi.category:
-                sys.argv.append('--category')
-                sys.argv.append('"'+mi.category+'"')
-            if (not options.freetext or options.freetext == 'Unknown') and mi.comments:
-                sys.argv.append('--comment')
-                sys.argv.append('"'+mi.comments+'"')
-            options, args, parser = html_parse_options(parser=parser)
-            process_file(html, options)
-        finally:
-            #try:
-                shutil.rmtree(tdir)
-            #except: # Windows can raise an error if some file is still being used
-            #    pass
-    except ConversionError, err:
-        print >>sys.stderr, err
-        sys.exit(1)
             
 if __name__ == '__main__':
-    main()
+    sys.exit(main())
     
         

src/libprs500/ebooks/lrf/txt/convert_from.py

@@ -19,33 +19,21 @@ import os, sys, codecs
 
 from libprs500 import iswindows
 from libprs500.ptempfile import PersistentTemporaryFile
-from libprs500.ebooks.lrf import option_parser
+from libprs500.ebooks.lrf import option_parser as lrf_option_parser
 from libprs500.ebooks import ConversionError
-from libprs500.ebooks.lrf.html.convert_from import parse_options as html_parse_options
 from libprs500.ebooks.lrf.html.convert_from import process_file
 from libprs500.ebooks.markdown import markdown
 
-def parse_options(argv=None, cli=True):
+def option_parser():
-    """ CLI for txt -> lrf conversions """
+    parser = lrf_option_parser('''Usage: %prog [options] mybook.txt\n\n'''
-    if not argv:
+        '''%prog converts mybook.txt to mybook.lrf''')
-        argv = sys.argv[1:]
-    parser = option_parser(
-        """usage: %prog [options] mybook.txt
-        
-        %prog converts mybook.txt to mybook.lrf
-        """
-        )
     defenc = 'cp1252' if iswindows else 'utf8'
     enchelp = 'Set the encoding used to decode ' + \
               'the text in mybook.txt. Default encoding is %default'
     parser.add_option('-e', '--encoding', action='store', type='string', \
                       dest='encoding', help=enchelp, default=defenc)
-    options, args = parser.parse_args(args=argv)
+    return parser
-    if len(args) != 1:
+    
-        if cli:
-            parser.print_help()
-        raise ConversionError, 'no filename specified'
-    return options, args, parser
 
 def generate_html(txtfile, encoding):
     '''
@@ -78,43 +66,22 @@ def generate_html(txtfile, encoding):
     codecs.open(p.name, 'wb', enc).write(html)
     return p
         
-def main():
+def main(args=sys.argv):
-    try:
+    parser = option_parser()    
-        options, args, parser = parse_options()
+    options, args = parser.parse_args(args)
-        txt = os.path.abspath(os.path.expanduser(args[0]))
+    if len(args) != 2:
-        p = generate_html(txt, options.encoding)
+        parser.print_help()
-        for i in range(1, len(sys.argv)):
+        print
-            if sys.argv[i] == args[0]:
+        print 'No txt file specified'
-                sys.argv.remove(sys.argv[i])
+        return 1
-                break            
+    txt = os.path.abspath(os.path.expanduser(args[1]))
-        sys.argv.append(p.name)
+    htmlfile = generate_html(txt, options.encoding)
-        sys.argv.append('--force-page-break-before')
+    options.force_page_break = 'h2'
-        sys.argv.append('h2')
+    if not options.output:
-        o_spec = False
+        ext = '.lrs' if options.lrs else '.lrf'
-        for arg in sys.argv[1:]:
+        options.output = os.path.basename(os.path.splitext(args[1])[0]) + ext                
-            arg = arg.lstrip()
-            if arg.startswith('-o') or arg.startswith('--output'):
-                o_spec = True
-                break
-        ext = '.lrf'
-        for arg in sys.argv[1:]:
-            if arg.strip() == '--lrs':
-                ext = '.lrs'
-                break
-        if not o_spec:
-            sys.argv.append('-o')
-            sys.argv.append(os.path.splitext(os.path.basename(txt))[0]+ext)
-        options, args, parser = html_parse_options(parser=parser)
-        src = args[0]
-        if options.verbose:
-            import warnings
-            warnings.defaultaction = 'error'        
-    except Exception, err:
-        print >> sys.stderr, err        
-        sys.exit(1)
-    process_file(src, options)
-        
     
+    process_file(htmlfile.name, options)
 
 if __name__ == '__main__':
-    main()
+    sys.exit(main())

src/libprs500/linux.py

@@ -16,8 +16,8 @@
 import sys, os
 from subprocess import check_call
 
-def options(parse_options):
+def options(option_parser):
-    options, args, parser = parse_options(['dummy'], cli=False) 
+    parser = option_parser() 
     options = parser.option_list
     for group in parser.option_groups:
         options += group.option_list
@@ -70,15 +70,16 @@ def setup_completion():
     try:
         print 'Setting up bash completion...',
         sys.stdout.flush()
-        from libprs500.ebooks.lrf.html.convert_from import parse_options as htmlop
+        from libprs500.ebooks.lrf.html.convert_from import option_parser as htmlop
-        from libprs500.ebooks.lrf.txt.convert_from import parse_options as txtop
+        from libprs500.ebooks.lrf.txt.convert_from import option_parser as txtop
-        from libprs500.ebooks.lrf.meta import parse_options as metaop
+        from libprs500.ebooks.lrf.meta import option_parser as metaop
         f = open('/etc/bash_completion.d/libprs500', 'wb')
         f.write('# libprs500 Bash Shell Completion\n')
         f.write(opts_and_exts('html2lrf', htmlop, 
                               ['htm', 'html', 'xhtml', 'xhtm', 'rar', 'zip', 'php']))
         f.write(opts_and_exts('txt2lrf', txtop, ['txt']))
-        f.write(opts_and_exts('lit2lrf', txtop, ['lit']))
+        f.write(opts_and_exts('lit2lrf', htmlop, ['lit']))
+        f.write(opts_and_exts('rtf2lrf', htmlop, ['rtf']))
         f.write(opts_and_exts('lrf-meta', metaop, ['lrf']))
         f.write('''
 _prs500_ls()