Logo Search packages:      
Sourcecode: babiloo version File versions  Download package


# -*- coding: utf-8 -*-
Copyright 2008 Serge Matveenko

This file is part of PyStarDict.

PyStarDict is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.

PyStarDict is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with PyStarDict.  If not, see <http://www.gnu.org/licenses/>.

@author: Serge Matveenko <s@matveenko.ru>
import gzip
import re
import os
from struct import unpack
from dictionary import DictionaryType, DictFormatError, Definition
import core.modules.utils as utils

    from hashlib import md5
    new_hash = md5
except ImportError:
    # Pre-2.5 Python has no hashlib module.
    import md5
    new_hash = md5.new

00037 class _StarDictIfo():
    The .ifo file has the following format:

    StarDict's dict ifo file

    Note that the current "version" string must be "2.4.2" or "3.0.0".  If it's not,
    then StarDict will refuse to read the file.
    If version is "3.0.0", StarDict will parse the "idxoffsetbits" option.

    In the example above, [options] expands to any of the following lines
    specifying information about the dictionary.  Each option is a keyword
    followed by an equal sign, then the value of that option, then a
    newline.  The options may be appear in any order.

    Note that the dictionary must have at least a bookname, a wordcount and a
    idxfilesize, or the load will fail.  All other information is optional.  All
    strings should be encoded in UTF-8.

    Available options:

    bookname=      // required
    wordcount=     // required
    synwordcount=  // required if ".syn" file exists.
    idxfilesize=   // required
    idxoffsetbits= // New in 3.0.0
    description=    // You can use <br> for new line.
    sametypesequence= // very important.
    def __init__(self, dict_prefix, container):

        ifo_filename = '%s.ifo' % dict_prefix

            _file = open(ifo_filename)
        except IOError:
            raise Exception('.ifo file does not exists')

        # skipping ifo header
        _line = _file.readline().split('=')
        if _line[0] == 'version':
            self.version = _line[1]
            raise Exception('ifo has invalid format')
        _config = {}
        for _line in _file:
            if _line and _line <> "\n":
                    _line_splited = _line.split('=')
                    _config[_line_splited[0]] = _line_splited[1]
                    print "Unrecognized paramater in IFO file at line: %s" % _line
        self.bookname = _config.get('bookname', None).strip()
        if self.bookname is None: raise Exception('ifo has no bookname')
        self.wordcount = _config.get('wordcount', None)
        if self.wordcount is None: raise Exception('ifo has no wordcount')
        self.wordcount = int(self.wordcount)
        if self.version == '3.0.0':
                _syn = open('%s.syn' % dict_prefix)
                self.synwordcount = _config.get('synwordcount', None)
                if self.synwordcount is None:
                    raise Exception('ifo has no synwordcount but .syn file exists')
                self.synwordcount = int(self.synwordcount)
            except IOError:

        self.idxfilesize = _config.get('idxfilesize', None)
        if self.idxfilesize is None: raise Exception('ifo has no idxfilesize')
        self.idxfilesize = int(self.idxfilesize)
        self.idxoffsetbits = _config.get('idxoffsetbits', 32)
        self.idxoffsetbits = int(self.idxoffsetbits)

        self.author = _config.get('author', '').strip()

        self.email = _config.get('email', '').strip()

        self.website = _config.get('website', '').strip()

        self.description = _config.get('description', '').strip()

        self.date = _config.get('date', '').strip()

        self.sametypesequence = _config.get('sametypesequence', '').strip()

00132 class _StarDictIdx():
    The .idx file is just a word list.

    The word list is a sorted list of word entries.

    Each entry in the word list contains three fields, one after the other:
         word_str;  // a utf-8 string terminated by '\0'.
         word_data_offset;  // word data's offset in .dict file
         word_data_size;  // word data's total size in .dict file

    def __init__(self, dict_prefix, container):

        idx_filename = '%s.idx' % dict_prefix
        idx_filename_gz = '%s.gz' % idx_filename

            file = open(idx_filename, 'rb')
        except IOError:
                file = gzip.open(idx_filename_gz, 'rb')
            except IOError:
                raise Exception('.idx file does not exists')

        # check file size
        self._file = file.read()
        if file.tell() != container.ifo.idxfilesize:
            raise Exception('size of the .idx file is incorrect')

        # prepare main dict and parsing parameters
        self._idx = {}
        idx_offset_bytes_size = int(container.ifo.idxoffsetbits / 8)
        idx_offset_format = {4: 'L', 8: 'Q',}[idx_offset_bytes_size]
        idx_cords_bytes_size = idx_offset_bytes_size + 4

        # parse data via regex
        record_pattern = r'([\d\D]+?\x00[\d\D]{%s})' % idx_cords_bytes_size
        matched_records = re.findall(record_pattern, self._file)

        # check records count
        if len(matched_records) != container.ifo.wordcount:
            raise Exception('words count is incorrect')

        # unpack parsed records
        for matched_record in matched_records:
            c = matched_record.find('\x00') + 1
            record_tuple = unpack('!%sc%sL' % (c, idx_offset_format),
            word, cords = record_tuple[:c-1], record_tuple[c:]
            self._idx[word] = cords  

00184     def __getitem__(self, word):
        returns tuple (word_data_offset, word_data_size,) for word in .dict

        @note: here may be placed flexible search realization
        if isinstance(word, unicode):
            word = word.encode('utf8')
        return self._idx[tuple(word)]

00194     def __contains__(self, k):
        returns True if index has a word k, else False
        return tuple(k) in self._idx

00200     def __eq__(self, y):
        returns True if md5(x.idx) is equal to md5(y.idx), else False
        return new_hash(self._file).digest() == new_hash(y._file).digest()

00206     def __ne__(self, y):
        returns True if md5(x.idx) is not equal to md5(y.idx), else False
        return not self.__eq__(y)

    def __len__(self):
        return len(self._idx)

00215 class _StarDictDict():
    The .dict file is a pure data sequence, as the offset and size of each
    word is recorded in the corresponding .idx file.

    If the "sametypesequence" option is not used in the .ifo file, then
    the .dict file has fields in the following order:
    word_1_data_1_type; // a single char identifying the data type
    word_1_data_1_data; // the data
    ...... // the number of data entries for each word is determined by
           // word_data_size in .idx file
    It's important to note that each field in each word indicates its
    own length, as described below.  The number of possible fields per
    word is also not fixed, and is determined by simply reading data until
    you've read word_data_size bytes for that word.

    Suppose the "sametypesequence" option is used in the .idx file, and
    the option is set like this:
    Then the .dict file will look like this:
    The first data entry for each word will have a terminating '\0', but
    the second entry will not have a terminating '\0'.  The omissions of
    the type chars and of the last field's size information are the
    optimizations required by the "sametypesequence" option described

    If "idxoffsetbits=64", the file size of the .dict file will be bigger
    than 4G. Because we often need to mmap this large file, and there is
    a 4G maximum virtual memory space limit in a process on the 32 bits
    computer, which will make we can get error, so "idxoffsetbits=64"
    dictionary can't be loaded in 32 bits machine in fact, StarDict will
    simply print a warning in this case when loading. 64-bits computers
    should haven't this limit.

    Type identifiers
    Here are the single-character type identifiers that may be used with
    the "sametypesequence" option in the .idx file, or may appear in the
    dict file itself if the "sametypesequence" option is not used.

    Lower-case characters signify that a field's size is determined by a
    terminating '\0', while upper-case characters indicate that the data
    begins with a network byte-ordered guint32 that gives the length of
    the following data's size(NOT the whole size which is 4 bytes bigger).

    Word's pure text meaning.
    The data should be a utf-8 string ending with '\0'.

    Word's pure text meaning.
    The data is NOT a utf-8 string, but is instead a string in locale
    encoding, ending with '\0'.  Sometimes using this type will save disk
    space, but its use is discouraged.

    A utf-8 string which is marked up with the Pango text markup language.
    For more information about this markup language, See the "Pango
    Reference Manual."
    You might have it installed locally at:

    English phonetic string.
    The data should be a utf-8 string ending with '\0'.

    Here are some utf-8 phonetic characters:

    A utf-8 string which is marked up with the xdxf language.
    See http://xdxf.sourceforge.net
    StarDict have these extention:
    <rref> can have "type" attribute, it can be "image", "sound", "video"
    and "attach".
    <kref> can have "k" attribute.

    Chinese YinBiao or Japanese KANA.
    The data should be a utf-8 string ending with '\0'.

    KingSoft PowerWord's data. The data is a utf-8 string ending with '\0'.
    It is in XML format.

    MediaWiki markup language.
    See http://meta.wikimedia.org/wiki/Help:Editing#The_wiki_markup

    Html codes.

    Resource file list.
    The content can be:
    img:pic/example.jpg     // Image file
    snd:apple.wav           // Sound file
    vdo:film.avi            // Video file
    att:file.bin            // Attachment file
    More than one line is supported as a list of available files.
    StarDict will find the files in the Resource Storage.
    The image will be shown, the sound file will have a play button.
    You can "save as" the attachment file and so on.

    wav file.
    The data begins with a network byte-ordered guint32 to identify the wav
    file's size, immediately followed by the file's content.

    Picture file.
    The data begins with a network byte-ordered guint32 to identify the picture
    file's size, immediately followed by the file's content.

    this type identifier is reserved for experimental extensions.

00349     def __init__(self, dict_prefix, container):
        opens regular or dziped .dict file
        self._container = container

        dict_filename = '%s.dict' % dict_prefix
        dict_filename_dz = '%s.dz' % dict_filename

            self._file = open(dict_filename, 'rb')
        except IOError:
                self._file = gzip.open(dict_filename_dz, 'rb')
            except IOError:
                raise Exception('.dict file does not exists')

00366     def __getitem__(self, word):
        returns data from .dict for word

        # getting word data coordinats
        cords = self._container.idx[word]

        # seeking in file for data

        # reading data
        bytes = self._file.read(cords[1])

        return bytes

    def __len__(self):
        return len(self.keys())

    def keys(self):
        return self._container.idx._idx.keys()

class _StarDictSyn():

    def __init__(self, dict_prefix, container):

        syn_filename = '%s.syn' % dict_prefix

            self._file = open(syn_filename)
        except IOError:
            # syn file is optional, passing silently

00401 class StarDict(DictionaryType):
    Dictionary-like class for lazy manipulating stardict dictionaries

    All items of this dictionary are writable and dict is expandable itself,
    but changes are not stored anywhere and available in runtime only.

    We assume in this documentation that "x" or "y" is instances of the
    StarDictDict class and "x.{ifo,idx{,.gz},dict{,.dz),syn}" or
    "y.{ifo,idx{,.gz},dict{,.dz),syn}" is files of the corresponding stardict

    Following documentation is from the "dict" class an is subkect to rewrite
    in further impleneted methods:

00417     def __init__(self, filename_prefix):
        filename_prefix: path to dictionary files without files extensions

        initializes new StarDictDict instance from stardict dictionary files
        provided by filename_prefix

        @todo: option to init from path to folder not from prefix
        DictionaryType.__init__(self, filename_prefix)

    def load(self, filename_prefix):
        if filename_prefix.endswith('.dict.dz'):
            filename_prefix = filename_prefix[:-len(('.dict.dz'))]
        elif filename_prefix.endswith('.dct.dz'):
            filename_prefix = filename_prefix[:-len(('.dct.dz'))]
        elif filename_prefix.endswith('.dict'):
            filename_prefix = filename_prefix[:-len(('.dict'))]
        elif filename_prefix.endswith('.dct'):
            filename_prefix = filename_prefix[:-len(('.dct'))]
        elif filename_prefix.endswith('.idx'):
            filename_prefix = filename_prefix[:-len(('.idx'))]
        elif filename_prefix.endswith('.ifo'):
            filename_prefix = filename_prefix[:-len(('.ifo'))]

        self.filename_prefix = filename_prefix
        #We want to have the same __hash value for the .idx .dz and .ifo files
        self._DictionaryType__filepath = "%s.ifo" % filename_prefix

            # reading somedict.ifo
            self.ifo = _StarDictIfo(dict_prefix=filename_prefix, container=self)
            # reading somedict.idx or somedict.idx.gz
            self.idx = _StarDictIdx(dict_prefix=filename_prefix, container=self)
            # reading somedict.dict or somedict.dict.dz
            self.dict = _StarDictDict(dict_prefix=filename_prefix, container=self)
        except Exception, e:
            raise DictFormatError, e

        # reading somedict.syn (optional)
        self.syn = _StarDictSyn(dict_prefix=filename_prefix, container=self)

        # initializing cache
        self._dict_cache = {}
        #Sorting keys 
        self._DictionaryType__keys = self.keys()
#        print self.idx._idx.keys()

00467     def keys(self):
        raises NotImplemented exception
        keys = []
        for tupled_word in self.dict.keys():
                print "Error with index ", tupled_word
        return keys

    def getTypeStr(self):
        return "StarDict"

    def getFilePath(self):
        dict_filename = '%s.dict' % self.filename_prefix
        dict_filename_dz = '%s.dz' % dict_filename
        dict_ifo = '%s.ifo' % self.filename_prefix
        dict_idx = '%s.idx' % self.filename_prefix

        return [dict_idx, dict_ifo, dict_filename, dict_filename_dz]

    def getName(self):
        return self.ifo.bookname.decode('utf-8')

00494     def __contains__(self, k):
        returns True if x.idx has a word k, else False
        return k in self.idx

00500     def __delitem__(self, k):
        frees cache from word k translation
        del self._dict_cache[k]

00506     def __getitem__(self, k):
        returns translation for word k from cache or not and then caches
        if isinstance(k, int):
            if len(self._dict_cache) > k:
                k = self._dict_cache.keys()[k]
                k = self.dict.keys()[k]
        if k in self._dict_cache:
            result = self._dict_cache[k]
            value = self.dict[k]
            self._dict_cache[k] = value
            result = value
        #print result
        return (k, Definition(result))

00524     def __len__(self):
        returns number of words provided by wordcount parameter of the x.ifo
        return self.ifo.wordcount

00530     def __repr__(self):
        returns classname and bookname parameter of the x.ifo
        return "StarDict <%s (%s)>" % (self.ifo.bookname, self.__len__())

00536     def clear(self):
        clear dict cache
        self._dict_cache = dict()

00542     def get(self, k, d=''):
        returns translation of the word k from self.dict or d if k not in x.idx

        d defaults to empty string
        return k in self and self[k] or d

00550     def has_key(self, k):
        returns True if self.idx has a word k, else False

        return k in self.keys()

Generated by  Doxygen 1.6.0   Back to index