Created
May 2, 2015 20:35
-
-
Save yvesf/d8cf8d647c88513a5e5e to your computer and use it in GitHub Desktop.
Parse google-chrome .pak files in shell
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
# Parse google-chrome .pak resourcefiles | |
parse_int() { | |
( echo "ibase=16; "; cat; echo -e "\n") | bc | |
} | |
endian_conversion() { | |
if [[ "$1" == "little" ]]; then | |
tac | |
else | |
cat | |
fi | |
} | |
read_bytes() { | |
local length=$1 | |
local endian=$2 | |
local i=0 | |
while [ $i -lt $length ]; do | |
read -r -d ' ' byte | |
[ "$byte" == "" ] && read -r -d ' ' byte | |
echo $byte | |
let i+=1 | |
done \ | |
| endian_conversion "$endian" \ | |
| tr -d '\n' | |
} | |
parse() { | |
local format=$1 | |
local endian=big | |
local i=0 | |
while [[ $i -lt ${#format} ]]; do | |
case "${format:$i:1}" in | |
"<") endian="little";; | |
">") endian="big";; | |
"I") read_bytes "4" "$endian" | parse_int; let offset+=4;; | |
"H") read_bytes "2" "$endian" | parse_int; let offset+=2;; | |
"B") read_bytes "1" "$endian" | parse_int; let offset+=1;; | |
*) | |
echo "Invalid format: ${format:$i:1}" >&2;; | |
esac | |
let i+=1 | |
done | tr '\n' ' ' | |
} | |
read_file() { | |
local file=$1 | |
local offset=$2 | |
local format=$3 | |
dd if=$file bs=1 skip=$offset count=$(format_len "$format") 2>/dev/null \ | |
| od --output-duplicates --format=x1 --address-radix=n \ | |
| tr 'a-z' 'A-Z' | tr -d '\n' | |
} | |
parse_file() { | |
read_file "$1" "$2" "$3" | parse "$3" | |
} | |
format_len() { | |
local format=$1 | |
local len=0 | |
local i=0 | |
while [[ $i -lt ${#format} ]]; do | |
case "${format:$i:1}" in | |
"I") let len+=4 ;; | |
"H") let len+=2 ;; | |
"B") let len+=1 ;; | |
"<"|">") ;; | |
*) echo "Invalid format: ${format:$i:1}" >&2;; | |
esac | |
let i+=1 | |
done | |
echo "$len" | |
} | |
################## | |
header_size=$(format_len "<IIB") | |
entry_size=$(format_len "<HI") | |
read -r version num_entries encoding < \ | |
<(parse_file "en-US.pak" 0 "<IIB") | |
if [ "$version" != "4" ]; then | |
echo "Invalid version: $version" >&2 | |
exit 1 | |
fi | |
if [ "$encoding" != "1" ]; then | |
echo "Invalid encoding: $encoding" >&2 | |
exit 1 | |
fi | |
pos=$header_size | |
i=0 | |
while [ $i -lt $num_entries ]; do | |
read -r id offset next_id next_offset < <(parse_file "en-US.pak" $pos "<HIHI") | |
let pos+=entry_size | |
let entry_len=next_offset-offset | |
echo "$id: $(dd if=en-US.pak bs=1 count=$entry_len skip=$offset 2>/dev/null)" | |
let i+=1 | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
for Windows you can also use 7zip with grit7z placed in
formats
folderor this bundle. should also work with Linux+wine.