Bug 672378

Created attachment 475087 [details]
Rust Documentation, HTML format (fails conversion)

Description of problem:

I am trying to read documentation on an e-book reader. The documentation is provided as .texi, so I converted to HTML via texi2html, and then loaded the HTML into Calibre, and asked it to convert to PDF and MOBI. Both fail with the same error. The HTML file in question is attached.


Version-Release number of selected component (if applicable):

0.7.38-3.fc14

Steps to Reproduce:

1. Add attached HTML file to library.
2. Convert individually with default options to PDF or MOBI.
3. Error is promptly displayed.

Actual Results:

The following error is given:

------------------------------------------
ERROR: Conversion Error: <b>Failed</b>: Convert book 1 of 1 (Rust Documentation)

Convert book 1 of 1 (Rust Documentation)
Processing archive...
Resolved conversion options
calibre version: 0.7.38
{'asciiize': True,
 'author_sort': None,
 'authors': None,
 'base_font_size': 0.0,
 'book_producer': None,
 'breadth_first': False,
 'change_justification': u'original',
 'chapter': u"//*[((name()='h1' or name()='h2') and re:test(., 'chapter|book|section|part|prologue|epilogue\\s+', 'i')) or @class = 'chapter']",
 'chapter_mark': u'pagebreak',
 'comments': None,
 'cover': None,
 'debug_pipeline': None,
 'disable_font_rescaling': False,
 'dont_compress': False,
 'dont_package': False,
 'extra_css': None,
 'font_size_mapping': None,
 'footer_regex': u'(?i)(?<=<hr>)((\\s*<a name=\\d+></a>((<img.+?>)*<br>\\s*)?\\d+<br>\\s*.*?\\s*)|(\\s*<a name=\\d+></a>((<img.+?>)*<br>\\s*)?.*?<br>\\s*\\d+))(?=<br>)',
 'header_regex': u'(?i)(?<=<hr>)((\\s*<a name=\\d+></a>((<img.+?>)*<br>\\s*)?\\d+<br>\\s*.*?\\s*)|(\\s*<a name=\\d+></a>((<img.+?>)*<br>\\s*)?.*?<br>\\s*\\d+))(?=<br>)',
 'html_unwrap_factor': 0.4,
 'input_encoding': '',
 'input_profile': <calibre.customize.profiles.InputProfile object at 0x3a94750>,
 'insert_blank_line': False,
 'insert_metadata': False,
 'isbn': None,
 'keep_ligatures': False,
 'language': None,
 'level1_toc': None,
 'level2_toc': None,
 'level3_toc': None,
 'line_height': 0.0,
 'linearize_tables': False,
 'margin_bottom': 5.0,
 'margin_left': 5.0,
 'margin_right': 5.0,
 'margin_top': 5.0,
 'max_levels': 5,
 'max_toc_links': 50,
 'minimum_line_height': 120.0,
 'mobi_ignore_margins': False,
 'no_chapters_in_toc': False,
 'no_inline_navbars': True,
 'no_inline_toc': False,
 'output_profile': <calibre.customize.profiles.KindleOutput object at 0x3a94d10>,
 'page_breaks_before': u"//*[name()='h1' or name()='h2']",
 'personal_doc': u'[PDOC]',
 'prefer_author_sort': False,
 'prefer_metadata_cover': False,
 'preprocess_html': False,
 'pretty_print': False,
 'pubdate': None,
 'publisher': None,
 'rating': None,
 'read_metadata_from_opf': '/tmp/calibre_0.7.38_tmp_r_4Wkt/calibre_0.7.38_FQbpxq.opf',
 'remove_first_image': False,
 'remove_footer': False,
 'remove_header': False,
 'remove_paragraph_spacing': False,
 'remove_paragraph_spacing_indent_size': 1.5,
 'rescale_images': False,
 'series': None,
 'series_index': None,
 'smarten_punctuation': False,
 'tags': None,
 'timestamp': None,
 'title': None,
 'title_sort': None,
 'toc_filter': None,
 'toc_threshold': 6,
 'toc_title': None,
 'use_auto_toc': False,
 'verbose': 2}
InputFormatPlugin: HTML Input running
on /tmp/calibre_0.7.38_tmp_r_4Wkt/calibre_0.7.38_Eedtrt_plumber/content.opf
Parsing all content...
Traceback (most recent call last):
  File "/usr/bin/calibre-parallel", line 19, in <module>
    sys.exit(main())
  File "/usr/lib64/calibre/calibre/utils/ipc/worker.py", line 106, in main
    result = func(*args, **kwargs)
  File "/usr/lib64/calibre/calibre/gui2/convert/gui_conversion.py", line 24, in gui_convert
    plumber.run()
  File "/usr/lib64/calibre/calibre/ebooks/conversion/plumber.py", line 853, in run
    accelerators, tdir)
  File "/usr/lib64/calibre/calibre/customize/conversion.py", line 216, in __call__
    log, accelerators)
  File "/usr/lib64/calibre/calibre/ebooks/html/input.py", line 299, in convert
    encoding=opts.input_encoding)
  File "/usr/lib64/calibre/calibre/ebooks/conversion/plumber.py", line 990, in create_oebbook
    reader()(oeb, path_or_stream)
  File "/usr/lib64/calibre/calibre/ebooks/oeb/reader.py", line 71, in __call__
    opf = self._read_opf()
  File "/usr/lib64/calibre/calibre/ebooks/oeb/reader.py", line 104, in _read_opf
    data = self.oeb.decode(data)
  File "/usr/lib64/calibre/calibre/ebooks/oeb/base.py", line 1897, in decode
    return fix_data(data.decode(self.input_encoding, 'replace'))
LookupError: unknown encoding: 
------------------------------------------