Error reading QuickDic6 on Android

[sobaee]

Hello Saeed
Thank you bro for your amazing app

These dictionaries from this link are Quickdic dictionaries v6:
https://github.com/rdoeffinger/Dictionary/releases

pyicu installed

This was the error:
↓↓↓↓

unhandled exception:
Traceback (most recent call last):
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/ui/ui_cmd_interactive.py", line 1123, in main
succeed = ui_cmd.UI.run(self, **self.getRunKeywordArgs())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/ui/ui_cmd.py", line 346, in run
finalOutputFile = self.glos.convert(
^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/glossary_v2.py", line 1267, in convert
return self.convertV2(args)
^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/glossary_v2.py", line 1216, in convertV2
sort = self._convertPrepare(
^^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/glossary_v2.py", line 1179, in _convertPrepare
self._read(
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/glossary_v2.py", line 789, in _read
self._openReader(reader, filenameUC)
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/glossary_v2.py", line 709, in _openReader
openResult = reader.open(filename)
^^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/plugins/quickdic6/reader.py", line 46, in open
self._dic = self.quickdic_from_path(self._filename)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/plugins/quickdic6/reader.py", line 56, in quickdic_from_path
return cls.quickdic_from_fp(fp)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/plugins/quickdic6/reader.py", line 71, in quickdic_from_fp
indices = read_list(fp, read_entry_index)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/plugins/quickdic6/read_funcs.py", line 99, in read_list
entries.append(fun(fp))
^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/plugins/quickdic6/read_funcs.py", line 150, in read_entry_index
stop_list = read_hashset(fp)
^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/plugins/quickdic6/read_funcs.py", line 82, in read_hashset
data.append(read_string(fp))
^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/plugins/quickdic6/read_funcs.py", line 63, in read_string
return mutf8.decode_modified_utf8(fp.read(length))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/plugin_lib/mutf8.py", line 47, in decode_modified_utf8
raise UnicodeDecodeError(
UnicodeDecodeError: 'mutf-8' codec can't decode byte 0x00 in position 4: Embedded NULL byte in input.
Traceback locals:
s = b'\x02tut\x00\x06Pluralt\x00\x06secondt\x00\x04thatt\x00\x03etct\x00...
len(s) = 29696
s_out = ['\x02', 't', 'u', 't']
s_len = 29696
s_ix = 5
b1 = 0

[ilius]

Which glossary are you converting?

Also what is your ICU version? Run

    python3 -c 'import icu; print(icu.VERSION)'

[sobaee]

• EN-DE.quickdic (I think the issue is the same with any one of them, just try the smaller one you prefer)

https://github.com/rdoeffinger/Dictionary/releases/download/v0.4-oldformat/EN-DE.quickdic.v006.zip

and I tried also with the same error with this:
https://github.com/rdoeffinger/Dictionary/releases/download/v0.4-dictionaries/EN-DE.quickdic.v007.zip

• ICU version 2.15.2 and tried also with 2.15.3 and still the exact same issue

[ilius]

I get a different exception for that file

[CRITICAL] Traceback (most recent call last):
  File "/home/s/pyglossary/main.py", line 10, in <module>
    main()
  File "/home/s/pyglossary/pyglossary/ui/main.py", line 313, in main
    sys.exit(mainNoExit(sys.argv))
             ^^^^^^^^^^^^^^^^^^^^
  File "/home/s/pyglossary/pyglossary/ui/main.py", line 291, in mainNoExit
    ok = run(
         ^^^^
  File "/home/s/pyglossary/pyglossary/ui/runner.py", line 77, in base_ui_run
    glos.convert(
  File "/home/s/pyglossary/pyglossary/glossary_v2.py", line 1283, in convert
    return self.convertV2(args)
           ^^^^^^^^^^^^^^^^^^^^
  File "/home/s/pyglossary/pyglossary/glossary_v2.py", line 1233, in convertV2
    sort = self._convertPrepare(
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/s/pyglossary/pyglossary/glossary_v2.py", line 1196, in _convertPrepare
    self._read(
  File "/home/s/pyglossary/pyglossary/glossary_v2.py", line 782, in _read
    self._openReader(reader, filenameUC)
  File "/home/s/pyglossary/pyglossary/glossary_v2.py", line 702, in _openReader
    openResult = reader.open(filename)
                 ^^^^^^^^^^^^^^^^^^^^^
  File "/home/s/pyglossary/pyglossary/plugins/quickdic6/reader.py", line 46, in open
    self._dic = self.quickdic_from_path(self._filename)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/s/pyglossary/pyglossary/plugins/quickdic6/reader.py", line 56, in quickdic_from_path
    return cls.quickdic_from_fp(fp)
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/s/pyglossary/pyglossary/plugins/quickdic6/reader.py", line 71, in quickdic_from_fp
    indices = read_list(fp, read_entry_index)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/s/pyglossary/pyglossary/plugins/quickdic6/read_funcs.py", line 100, in read_list
    entries.append(fun(fp))
                   ^^^^^^^
  File "/home/s/pyglossary/pyglossary/plugins/quickdic6/read_funcs.py", line 153, in read_entry_index
    assert pos == stop_list_offset + stop_list_size, (
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError: pos=201700245, stop_list_offset=201699842, stop_list_size=401

Maybe try reporting it on QuickDic repo and make sure files are not corrupted.

[sobaee]

Hello Saeed
The new fix is dealing better with these files, since it is converted a part of the file but this error has occurred :

Converting: %54.5 |██████▌ |[00:10<00:05, 11.36s/it]unhandled exception:
Traceback (most recent call last):
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/ui/ui_cmd_interactive.py", line 1124, in main
succeed = ui_cmd.UI.run(self, **self.getRunKeywordArgs())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/ui/ui_cmd.py", line 346, in run
finalOutputFile = self.glos.convert(
^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/glossary_v2.py", line 1283, in convert
return self.convertV2(args)
^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/glossary_v2.py", line 1248, in convertV2
finalOutputFile = self._write(
^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/glossary_v2.py", line 994, in _write
self._writeEntries(writerList, filename, options)
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/glossary_v2.py", line 934, in _writeEntries
for entry in self:
^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/glossary_v2.py", line 441, in _readersEntryGen
yield from iterator
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/glossary_v2.py", line 460, in _applyEntryFiltersGen
entry = entryFilter.run(entry) # noqa: PLW2901
^^^^^^^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/entry_filters.py", line 127, in run
entry.editFuncDefi(fixUtf8Str)
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/entry.py", line 359, in editFuncDefi
self._defi = func(self._defi)
^^^^^^^^^^^^^^^^
File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/pyglossary/text_utils.py", line 65, in fixUtf8Str
return st.encode("utf-8").replace(b"\x00", b"").decode("utf-8", "replace")
^^^^^^^^^^^^^^^^^^
UnicodeEncodeError: 'utf-8' codec can't encode character '\udf70' in position 145: surrogates not allowed
Traceback locals:
st = '

Etymology

\nPossibly from {{bor|de|nl|China}}, from possibl...
len(st) = 1509