lib/region: Start working on region file parser

Something is fishy with dumpnbt or lib/nbt.
Attempting to dump the extracted chunk fails, but external tools
do manage to parse it.

resources/region_files/first_chunk.sh

@@ -0,0 +1,74 @@
+if [ "$1" = "-v" ]; then
+    VERBOSE=true
+    shift
+else
+    VERBOSE=false
+fi
+
+if [ ! -f "$1" ]; then
+    echo "Usage: $0 [-v] FILE"
+    echo "  -v   display raw content and NBT dump"
+    exit 1
+fi
+
+# pointer data
+OFFSET_HEX="0x$(dd bs=1 if="$1" count=3 2>/dev/null | hexdump -e '3/1 "%02x" "\n"')"
+OFFSET="$(baseconvert -d $OFFSET_HEX)"
+echo "  offset: $OFFSET ($OFFSET_HEX)"
+LENGTH_HEX="0x$(dd bs=1 if="$1" count=1 skip=3 2>/dev/null | hexdump -e '1/1 "%02x" "\n"')"
+LENGTH="$(baseconvert -d $LENGTH_HEX)"
+echo "  length: $LENGTH ($LENGTH_HEX)"
+
+#TODO: last modified
+
+# chunk
+DATA="$(dd if="$1" bs=4096 count=$LENGTH skip=$OFFSET 2>/dev/null | hexdump -v -e '16/1 "%02x" "\n"' | tr -d '
+')"
+
+# blob header
+# bs=2 because each byte is two digits hex
+COMPRESSED_LENGTH_HEX="0x$(dd bs=2 count=4 2> /dev/null <<< $DATA)"
+COMPRESSED_LENGTH="$(baseconvert -d $COMPRESSED_LENGTH_HEX)"
+echo "  compressed length in bytes: $COMPRESSED_LENGTH ($COMPRESSED_LENGTH_HEX)"
+FORMAT_HEX="0x$(dd bs=2 skip=4 count=1 2> /dev/null <<< $DATA)"
+case $FORMAT_HEX in
+"0x01")
+    FORMAT="gzip"
+    function UNCOMPRESS {
+        gzip -dc
+    }
+    ;;
+"0x02")
+    FORMAT="zlib"
+    function UNCOMPRESS {
+        cat > /tmp/chunk_zlib_decompress
+        python3 <<< "
+import zlib,sys
+a = open('/tmp/chunk_zlib_decompress', 'rb')
+data = a.read()
+a.close()
+sys.stdout.buffer.write(zlib.decompress(data))
+sys.stdout.buffer.flush()
+"
+        rm /tmp/chunk_zlib_decompress
+    }
+    ;;
+*)
+    FORMAT="unknown"
+    function UNCOMPRESS {
+        false
+    }
+    ;;
+esac
+echo "  format: $FORMAT ($FORMAT_HEX)"
+
+if $VERBOSE; then
+    echo "Raw chunk data:"
+    echo "$DATA"
+    echo "NBT dump:"
+
+    #TODO: use pipes instead of a file
+    dd if="$1" bs=4096 count=$LENGTH skip=$OFFSET 2>/dev/null | dd bs=1 skip=5 count=$(($COMPRESSED_LENGTH-1)) 2>/dev/null | UNCOMPRESS > /tmp/chunk_uncompressed_nbt
+    dumpnbt /tmp/chunk_uncompressed_nbt
+    rm /tmp/chunk_uncompressed_nbt
+fi

src/lib/region.cpp

@@ -0,0 +1,17 @@
+// Copyright 2023, FOSS-VG Developers and Contributers
+//
+// Author(s):
+//   BodgeMaster
+//
+// This program is free software: you can redistribute it and/or modify it
+// under the terms of the GNU Affero General Public License as published
+// by the Free Software Foundation, version 3.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied
+// warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+// See the GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// version 3 along with this program.
+// If not, see https://www.gnu.org/licenses/agpl-3.0.en.html

src/lib/region.hpp

@@ -0,0 +1,57 @@
+// Copyright 2023, FOSS-VG Developers and Contributers
+//
+// Author(s):
+//   BodgeMaster
+//
+// This program is free software: you can redistribute it and/or modify it
+// under the terms of the GNU Affero General Public License as published
+// by the Free Software Foundation, version 3.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied
+// warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+// See the GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// version 3 along with this program.
+// If not, see https://www.gnu.org/licenses/agpl-3.0.en.html
+
+
+// File structure:
+//  4K table of uint32_t: pointing to chunks
+//    -> 24bit offset, 8 bit length
+//      -> both offset and length are multiplied by 4096 to get the real value
+//      -> lowest valid offset = 2
+//      -> chunk is not present if pointer=0
+//    -> chunk calculation: ((x % 32) + (z % 32) * 32) * 4
+//      -> what about negative chunks?
+//  4k table of uint32_t: last modified timestamps
+//  individual chunks
+//    -> 5 byte header
+//      -> 4 byte length
+//      -> 1 byte compression type: 0?? 1->gzip 2->zlib
+//        -> extension idea: support for other compression algorithms
+//          - lzma
+//          - xz
+//          - lz4
+//          - zstd
+//    -> compressed NBT data
+
+#pragma once
+
+#include <cstdint>
+
+class Region {
+    uint32_t storagePointers[1024];
+    uint32_t lastModifiedTimestamps[1024];
+
+    // Chunk coordinates are uint8_t here bc they are 0<=x<32.
+    uint32_t* coordsToStoragePointer(uint8_t x, uint8_t z) {
+        return &storagePointers[z*32 + x];
+    }
+
+    // Chunk coordinates are uint8_t here bc they are 0<=x<32.
+    uint32_t* coordsToLastModified(uint8_t x, uint8_t z) {
+        return &lastModifiedTimestamps[z*32 + x];
+    }
+}