Skip to content

Instantly share code, notes, and snippets.

@josephg
Last active February 16, 2024 08:33
Show Gist options
  • Star 95 You must be signed in to star a gist
  • Fork 24 You must be signed in to fork a gist
  • Save josephg/5e134adf70760ee7e49d to your computer and use it in GitHub Desktop.
Save josephg/5e134adf70760ee7e49d to your computer and use it in GitHub Desktop.
Apple dictionaries
# Thanks to commenters for providing the base of this much nicer implementation!
# Save and run with $ python 0dedict.py
# You may need to hunt down the dictionary files yourself and change the awful path string below.
# This works for me on MacOS 10.14 Mohave
from struct import unpack
from zlib import decompress
import re
filename = '/System/Library/Assets/com_apple_MobileAsset_DictionaryServices_dictionaryOSX/9f5862030e8f00af171924ebbc23ebfd6e91af78.asset/AssetData/Oxford Dictionary of English.dictionary/Contents/Resources/Body.data'
f = open(filename, 'rb')
def gen_entry():
f.seek(0x40)
limit = 0x40 + unpack('i', f.read(4))[0]
f.seek(0x60)
while f.tell()<limit:
sz, = unpack('i', f.read(4))
buf = decompress(f.read(sz)[8:])
pos = 0
while pos < len(buf):
chunksize, = unpack('i', buf[pos:pos+4])
pos += 4
entry = buf[pos:pos+chunksize]
title = re.search('d:title="(.*?)"', entry).group(1)
yield title, entry
pos += chunksize
for word, definition in gen_entry():
print(word)
// *** Old code - not needed given the python code above
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <assert.h>
#include "zlib.h"
#define CHUNK 16384
/*
40 Length of the zlib stream
4c 0020
54 0275 number of blocks
60 808c pointer to the next block
64 8088 length of the first block
68 047a4a length of the unpacked block
6c start of the zlib stream
80fc second block
13cd134
13cd174
*/
int unpack(unsigned char *in, int len)
{
int ret,outed=0;
unsigned have;
z_stream strm;
unsigned char out[CHUNK];
strm.zalloc = Z_NULL;
strm.zfree = Z_NULL;
strm.opaque = Z_NULL;
strm.avail_in = 0;
strm.next_in = Z_NULL;
ret = inflateInit(&strm);
if (ret != Z_OK)
return ret;
strm.avail_in = len;
strm.next_in = in;
do {
strm.avail_out = CHUNK;
strm.next_out = out;
ret = inflate(&strm, Z_NO_FLUSH);
assert(ret != Z_STREAM_ERROR); /* state not clobbered */
switch (ret) {
case Z_NEED_DICT:
ret = Z_DATA_ERROR; /* and fall through */
case Z_DATA_ERROR:
case Z_MEM_ERROR:
(void)inflateEnd(&strm);
return ret;
}
// printf("%lx %x\n",strm.next_in-in,strm.avail_in);
have = CHUNK - strm.avail_out /* - (outed?0:4)*/;
int off = 0;
/*
while (have - off > 3 && out[off] != '<' && out[1+off] != 'd' && out[2+off] != ':') {
++off;
}*/
if (have - off <= 3) {
fprintf(stderr, "could not find entry\n");
}
if (fwrite(out + off/*+(outed?0:4)*/, have - off, 1, stdout) != 1 || ferror(stdout)) {
(void)inflateEnd(&strm);
return Z_ERRNO;
}
//exit(0);
outed+=have;
} while (strm.avail_out == 0);
printf("%06x\n",outed);
(void)inflateEnd(&strm);
return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR;
}
char filename[256];
int main(int argc,char **argv) {
FILE *fin; int limit,blen=0,p,l,bcnt=0; unsigned char *buf=NULL;
assert(argc >= 2);
sprintf(filename,"/Library/Dictionaries/%s.dictionary/Contents/Body.data",argv[1]);
if((fin=fopen(filename,"rb"))) {
fseek(fin,0x40,SEEK_SET);
fread(&l,1,4,fin);
limit=0x40+l;
p=0x60;
do {
fseek(fin,p,SEEK_SET);
fread(&l,1,4,fin);
// if(0==l) break;
if(blen<l) {
if(buf!=NULL) free(buf);
blen=l;
buf=(unsigned char *)malloc(blen);
}
fread(buf,1,l,fin);
//fprintf(stderr, "%x@%06x: %x>%06x\n",bcnt,p,l,((int *)buf)[1]);
unpack(buf+8,l-8);
p+=4+l;
++bcnt;
} while(p<limit);
free(buf);
fclose(fin);
}
return 0;
}
// This program strips the first 4 characters from each line in the input
#include <stdio.h>
int main() {
while(!ferror(stdin) && !feof(stdin)) {
size_t len = 0;
char *line = fgetln(stdin, &len);
if (!line) break;
if (len > 4)
fwrite(line + 4, 1, len - 4, stdout);
}
return 0;
}
@swadevs
Copy link

swadevs commented Nov 1, 2018

@josephg @korakot The python program above provides the list of words but not their derivatives. For example, it has the word 'walk' but not the words such as 'walks', 'walking', 'walked' etc. Is this possible to get those words as well somehow?
Do you know what other data files (e.g. EntryID.data, KeyText.data) contain? May be they have such mapping!

@wyatttu
Copy link

wyatttu commented Nov 13, 2018

Following

@peheje
Copy link

peheje commented May 28, 2019

I get the error: "cannot use a string pattern on a bytes-like object" on the line:
title = re.search('d:title="(.*?)"', entry).group(1)

Which version of python are you running?
Also would love to see derivates like @swadevs mentioned

@atylmo
Copy link

atylmo commented Jul 8, 2019

@peheje I got it to work with the built-in Python 2 on Mac. Python 3 gives me the same error as you.

@ctrngk
Copy link

ctrngk commented Jul 21, 2019

Other than Body.data, there are still two *.data for indexing. For example, when you type something similar, it will be redirected to the right title. Are anybody able to extract it?

I try to use the same code. It is not working for the rest of *.data.

@vinniec
Copy link

vinniec commented Aug 17, 2019

Today I tried this program because I wanted to convert an apple dictionary to another format but starting the script 0dedict.py I get this error:

$ python3 ./0dedict.py 
Traceback (most recent call last):
  File "./0dedict.py", line 33, in <module>
    for word, definition in gen_entry():
  File "./0dedict.py", line 20, in gen_entry
    buf = decompress(f.read(sz)[8:])
MemoryError

The same also with python2.
This is the source of dictionary: http://rssmac.altervista.org/download/files/italian.dictionary.zip

@vinniec
Copy link

vinniec commented Aug 17, 2019

I tried to go through the code a little bit to see if I could figure out where the mistake was.
It seems to me that the error occurs at line 25 18, in the instruction "f.read(sz)".
In this case I think that sz has a value too large (1919866155, sorry, I do not know the unit of measurement but I think they are bytes and so I think it is a wrong value, if I have calculated correctly I'm asking him to read 1.8gb but the file Body.data is large 34mb).
Is it possible that the dictionary is not well formed?

@vinniec
Copy link

vinniec commented Aug 18, 2019

After a lot of test I can say that maybe the dictionary that interests me is damaged, not well formed or the dictionaries can have different forms.
However to your script on line 25 I would postpend .decode('utf-8') and I would remove line 23

@ilius
Copy link

ilius commented Aug 19, 2019

Any ideas how can we get the number of entries at the beginning, without reading the whole file?

@vinniec
Copy link

vinniec commented Aug 22, 2019

Based on the structure of the body.data file that I deduced from this script this information is not there, but I think that this information could be in the other files (one of these EntryID.data, EntryID.index, KeyText.data, KeyText.index)

@pizzacloud
Copy link

I tried, but failed. I don't know much about pragraming, but this is very important to me, could you please help me?
Many thanks!
Here is the screenshot:
image

@vinniec
Copy link

vinniec commented Oct 30, 2019

Please, try with pyglossary: ilius/pyglossary#109
A lot of time has passed since my tests and all the tests I did are on the old pc.
So you could do the tests for this new feature instead of me.

@kiemrong08
Copy link

@josephg That's interesting, but how to extract both word and definition ?

@Apochrosi
Copy link

I'm getting this error here, does anyone by any chance know how to fix it?

Deluges-MacBook-Air:app Deluge$ python 0dedict.py
Traceback (most recent call last):
  File "0dedict.py", line 31, in <module>
    for word, definition in gen_entry():
  File "0dedict.py", line 18, in gen_entry
    buf = decompress(f.read(sz)[8:])
zlib.error: Error -3 while decompressing data: incorrect header check
Deluges-MacBook-Air:app Deluge$ 

@vinniec
Copy link

vinniec commented Mar 4, 2020

Not me, I have the idea that they have changed the compression format of the dictionary entries and therefore I can't help you. At the time I tried with a Hex Editor to understand the pattern of a term, but I don't know if this tip it can help you.

@vinniec
Copy link

vinniec commented Mar 4, 2020

or maybe you have the same my old problem, and I can help you. In my dict the header of every compressed dict is wrongso i decompress every term only attempting a lot of time.

@Apochrosi
Copy link

It's this file here I have been trying to uncompress. It might be compressed a bit different than the regular dictionaries and that might be the problem.

"/System/Library/Input Methods/JapaneseIM.app/Contents/Plugins/JapaneseIM.appex/Contents/Resources/CharacterInfo.dictionary"

@tcardlab
Copy link

For those receiving "cannot use a string pattern on a bytes-like object" error, just str(entry).

@asnahu
Copy link

asnahu commented Mar 13, 2021

In python3, for unicode strings, should change the following lines:

title = re.search('d:title="(.*?)"', entry).group(1) to title = re.search(b'd:title="(.*?)"', entry).group(1)

and

print(word) to print(word.decode("UTF-8"))

it will generate correct string, if not, will get an error: cannot use a string pattern on a bytes-like object.

@jukhamil
Copy link

Hey,
So just to be clear, we can use this script to spit out all the entries in an Apple dictionary, which we choose ourselves what format we want to save in?
Thanks,
Julius

@spidertwin2
Copy link

Hello,

I am trying to read the dictionary inside a simple react arrow function, but am a little lost with making decompression work correctly. I am stuck at the output <Buffer 00 00 00 00 ... >

If anybody has managed to make the extraction work with JS, please let me know. Thanks!

🦕

@josephg
Copy link
Author

josephg commented Sep 13, 2021

Way more up to date info here: https://fmentzer.github.io/posts/2020/dictionary/

@soshial
Copy link

soshial commented Dec 25, 2022

I would like to extract morphological forms from binary AppleDict. I struggled with these files and didn't succeed:

EntryID.index
EntryID.data
KeyText.index
KeyText.data

If anyone succeeds deciphering those, I would be very grateful.

@soshial
Copy link

soshial commented Jan 26, 2023

I was able to extract morphological forms from binary AppleDict (contained in KeyText.data) and exact article addresses from EntryID.data. Thank you @josephg and @fab-jul for inspiring me to do that.

On this pyglossary issue page you may find KeyText.data and EntryID.data format description in detail with code.

UPD (4 Mar 2023). We merged functionality that supports export of keys/indexing/morphology in AppleDict.

@fhefh2018
Copy link

macOS 12.6.3
The folder is: /System/Library/AssetsV2/com_apple_MobileAsset_DictionaryServices_dictionaryOSX

@tsunho12
Copy link

tsunho12 commented May 1, 2023

macOS 13.3.1
Thank you provided this code. On my device, I tried to make some fixes to make it work properly.

# Thanks to commenters for providing the base of this much nicer implementation!
# Save and run with $ python 0dedict.py
# You may need to hunt down the dictionary files yourself and change the awful path string below.
# This works for me on MacOS 10.14 Mohave

from struct import unpack
from zlib import decompress
import re


filename = " "


f = open(filename, 'rb')

def gen_entry():
    f.seek(0x40)
    limit = 0x40 + unpack('i', f.read(4))[0]
    f.seek(0x60)
    while f.tell()<limit:
        sz, = unpack('i', f.read(4))
        buf = decompress(f.read(sz)[8:])

        pos = 0
        while pos < len(buf):
            chunksize, = unpack('i', buf[pos:pos+4])
            pos += 4

            entry = buf[pos:pos+chunksize]
            title = re.search(b'd:title="(.*?)"', entry).group(1).decode('utf-8')
            yield title, entry

            pos += chunksize

for word, definition in gen_entry():
    print(word)

@soshial
Copy link

soshial commented May 1, 2023

@tsunho12 you will get much better convertion results if you use https://github.com/ilius/pyglossary

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment