git clone https://github.com/mar1mo-41414/SonyNasne-debian.git
cd SonyNasne-debian
python3 scripts/nasne_setup.py check

  [OK] python3                    このツール、.dlm の作成
  [OK] curl                       GPLソース・公式ファームの取得
  [OK] bzip2                      カーネルソースの展開
  [OK] tar
  [OK] file                       ツリー作成時のバイナリ検査
  [NG] docker                   ← apt: docker.io  カーネルのビルド(古いgcc 4.3.2のコンテナ)
  [NG] debootstrap              ← apt: debootstrap  Debian wheezy (mipsel) の作成
  [NG] qemu-mipsel-static       ← apt: qemu-user-static  mipselのDebianをPC上で実行(debootstrapの第2段階)
  [--] mipsel-linux-gnu-gcc     ← apt: gcc-mipsel-linux-gnu  MIPS用ツールのビルド(無ければDockerのgccで代用)
  [NG] binfmt の qemu-mipsel が未登録 ← apt: binfmt-support(登録されない場合は update-binfmts --enable qemu-mipsel)

足りないもの(Debian/Ubuntu): sudo apt install binfmt-support debootstrap docker.io qemu-user-static

sudo apt update
sudo apt install binfmt-support debootstrap docker.io qemu-user-binfmt

python3 scripts/nasne_setup.py check

-rwxr-xr-x 1 root root 4211448 Sep  2 18:18 /usr/bin/qemu-mipsel
/usr/bin/qemu-mipsel-static: cannot open `/usr/bin/qemu-mipsel-static' (No such file or directory)
enabled
interpreter /usr/bin/qemu-mipsel
flags: POF
offset 0
magic 7f454c46010101000000000000000000020008000100000000000000000000000000000000000000
mask ffffffffffffff0000fffffffffffffffeffffffffffffff00000000000000000000000020000000
  [OK] python3                    このツール、.dlm の作成
  [OK] curl                       GPLソース・公式ファームの取得
  [OK] bzip2                      カーネルソースの展開
  [OK] tar
  [OK] file                       ツリー作成時のバイナリ検査
  [OK] docker                     カーネルのビルド(古いgcc 4.3.2のコンテナ)
  [OK] debootstrap                Debian wheezy (mipsel) の作成
  [NG] qemu-mipsel-static       ← apt: qemu-user-static  mipselのDebianをPC上で実行(debootstrapの第2段階)
  [--] mipsel-linux-gnu-gcc     ← apt: gcc-mipsel-linux-gnu  MIPS用ツールのビルド(無ければDockerのgccで代用)
  [NG] docker を実行できない(権限またはデーモン): permission denied while trying to connect to the docker API at unix:///var/run/docker.sock

足りないもの(Debian/Ubuntu): sudo apt install qemu-user-static
  (dockerの権限: sudo usermod -aG docker $USER など)

sudo ln -s /usr/bin/qemu-mipsel /usr/local/bin/qemu-mipsel-static

sudo usermod -aG docker $USER

wsl --shutdown

cd ~/SonyNasne-debian
python3 scripts/nasne_setup.py check

docker OK
  [OK] python3                    このツール、.dlm の作成
  [OK] curl                       GPLソース・公式ファームの取得
  [OK] bzip2                      カーネルソースの展開
  [OK] tar
  [OK] file                       ツリー作成時のバイナリ検査
  [OK] docker                     カーネルのビルド(古いgcc 4.3.2のコンテナ)
  [OK] debootstrap                Debian wheezy (mipsel) の作成
  [OK] qemu-mipsel-static         mipselのDebianをPC上で実行(debootstrapの第2段階)
  [--] mipsel-linux-gnu-gcc     ← apt: gcc-mipsel-linux-gnu  MIPS用ツールのビルド(無ければDockerのgccで代用)

必要なものはそろっています。

ssh-keygen -t rsa -b 4096 -f ~/.ssh/nasne_rsa

cd ~/SonyNasne-debian
python3 scripts/nasne_setup.py build --download-official \
  --ssh-pubkey ~/.ssh/nasne_rsa.pub --work build_nasne 2>&1 | tee build.log

Get:20 http://archive.debian.org/debian/ wheezy/main openssh-client mipsel 1:6.0p1-4+deb7u4 [979 kB]
Get:21 http://archive.debian.org/debian/ wheezy/main openssh-server mipsel 1:6.0p1-4+deb7u4 [318 kB]
Get:22 http://archive.debian.org/debian/ wheezy/main tcpd mipsel 7.6.q-24 [26.3 kB]
Get:23 http://archive.debian.org/debian/ wheezy/main xauth mipsel 1:1.0.7-1 [35.6 kB]
Preconfiguring packages ...
Fetched 9230 kB in 1s (7718 kB/s)
Can not write log, openpty() failed (/dev/pts not mounted?)

cd ~/SonyNasne-debian
sudo rm -rf build_nasne/tree
python3 scripts/nasne_setup.py build --download-official \
  --ssh-pubkey ~/.ssh/nasne_rsa.pub --work build_nasne < /dev/null 2>&1 | tee build.log

== ステップ 1: 公式ファームパッケージ
  /home/xxx/SonyNasne-debian/build_nasne/KRST3101_0260_SECURE.dlm (36119466 バイト)

== ステップ 2: カーネルのGPLソース(Sony公開)
  展開済み

== ステップ 3: カーネル用ツールチェーン(Dockerイメージ nasne-kcc:gcc432。gcc 4.3.2 + binutils 2.19.1 をビルド。30分〜1時間)
  イメージあり

== ステップ 4: 自作カーネルのビルド(直起動用の内蔵initramfs入り)
  /home/xxx/SonyNasne-debian/gpl_src/build/out/vmlinux_new.bin あり

== ステップ 5: KNLセグメント(公式のKNLを雛形に、自作カーネルを包む)
  $ /usr/bin/python3 /home/xxx/SonyNasne-debian/scripts/build_knl.py verify /home/xxx/SonyNasne-debian/build_nasne/knl_new.bin

== ステップ 6: Debian wheezy (mipsel) のツリー(debootstrap。数分)
  $ sudo /home/xxx/SonyNasne-debian/scripts/stage1/prepare_tree.sh --out /home/xxx/SonyNasne-debian/build_nasne/tree --knl /home/xxx/SonyNasne-debian/build_nasne/knl_new.bin --official /home/xxx/SonyNasne-debian/build_nasne/KRST3101_0260_SECURE.dlm --ssh-pubkey /home/xxx/.ssh/nasne_rsa.pub
  $ sudo tar --numeric-owner -cpf /home/xxx/SonyNasne-debian/build_nasne/debian_tree.tar -C /home/xxx/SonyNasne-debian/build_nasne/tree .
  $ sudo chown 1000:1000 /home/xxx/SonyNasne-debian/build_nasne/debian_tree.tar

== ステップ 7: 00550066.dlm の作成
  --hdd-dlm が無いので、ここで止めます。ビルドは完了しています。HDDの00550066.dlmを用意して、もう一度 build を実行してください(以前のステップは飛ばされます)。

Get-CimInstance -Query "SELECT * from Win32_DiskDrive" | Select-Object DeviceID, Model, Size

DeviceID           Model                                      Size
--------           -----                                      ----
\\.\PHYSICALDRIVE5 HGST HTS 541010A9E680 USB Device  1000202273280

wsl --mount \\.\PHYSICALDRIVE5 --bare

lsblk -o NAME,SIZE,FSTYPE,LABEL

NAME     SIZE FSTYPE LABEL
sda    356.9M ext4
sdb    159.4M ext4
sdc     48.8G swap
sdd        1T ext4
sde    931.5G
├─sde1   256M ext3   sys1
├─sde2     1G ext3   sys2
└─sde3 930.3G xfs    user

cd ~/SonyNasne-debian
sudo mkdir -p /mnt/nasne_sys1
sudo mount /dev/sde1 /mnt/nasne_sys1
findmnt /mnt/nasne_sys1
ls -la /mnt/nasne_sys1
df -h /mnt/nasne_sys1

TARGET          SOURCE    FSTYPE OPTIONS
/mnt/nasne_sys1 /dev/sde1 ext3   rw,relatime,stripe=4
total 31047
drwxr-xr-x  5 root root     1024 Jan  1  1970 .
drwxr-xr-x 10 root root     4096 Oct 28 03:17 ..
-rw-r--r--  1 root root      148 Apr 28  2018 00110022.dlm
-rwxr-xr-x  1 root root 31646110 Apr 28  2018 00550066.dlm
drwx------  2 root root     1024 Apr 28  2018 11002200
drwx------  2 root root     1024 May 20  2017 33004400
drwx------  2 root root    12288 Jul 26  2013 lost+found
Filesystem      Size  Used Avail Use% Mounted on
/dev/sde1       238M  100M  126M  45% /mnt/nasne_sys1

mkdir -p backup
cp /mnt/nasne_sys1/00550066.dlm backup/00550066.dlm.orig
sha256sum /mnt/nasne_sys1/00550066.dlm backup/00550066.dlm.orig
mkdir -p /mnt/c/nasne_backup
cp backup/00550066.dlm.orig /mnt/c/nasne_backup/

39a3a436bace9c3fa4a252a9272cf5715afb6e0b3af695c76d73050aa22014c8  /mnt/nasne_sys1/00550066.dlm
39a3a436bace9c3fa4a252a9272cf5715afb6e0b3af695c76d73050aa22014c8  backup/00550066.dlm.orig

python3 scripts/stage1/make_stage1_dlm.py build --official backup/00550066.dlm.orig \
  --out spi_backup.dlm --mode backup

公式rootfs: tar 86026240 bytes、ヘッダ date='Tue Oct 24 11:13:25 2017\x00\x00\x00\x00\x00\x00\x00\x00' +8(major)=2
rcS のエントリ: 2個(最後の #474 を差し替える)
新しいボディ: 31605881 bytes (31.6MB)  公式のエントリ数 1289
spi_backup.dlm: 31605945 bytes  自己検証=OK flag=0 crc=True
読み戻し検証OK: エントリ 1289(元 1289)、rcS 差し替え済み、mode=backup

sudo bash scripts/stage1/install_dlm.sh /mnt/nasne_sys1 spi_backup.dlm --backup-dir ./backup_sys1
ls -la /mnt/nasne_sys1
sync
sudo umount /mnt/nasne_sys1

検査OK: hwtype・日付が一致、CRC OK
退避: ./backup_sys1/00550066.dlm.orig
書き込み完了: /mnt/nasne_sys1/00550066.dlm
/dev/sde1       238M  100M  126M  45% /mnt/nasne_sys1
total 31008
drwxr-xr-x  5 root root     1024 Oct 28 03:24 .
drwxr-xr-x 10 root root     4096 Oct 28 03:17 ..
-rw-r--r--  1 root root      148 Apr 28  2018 00110022.dlm
-rw-r--r--  1 root root 31605945 Oct 28 03:24 00550066.dlm
drwx------  2 root root     1024 Apr 28  2018 11002200
drwx------  2 root root     1024 May 20  2017 33004400
drwx------  2 root root    12288 Jul 26  2013 lost+found

wsl --unmount \\.\PHYSICALDRIVE5

Get-CimInstance -Query "SELECT * from Win32_DiskDrive" | Select-Object DeviceID, Model, Size

wsl --mount \\.\PHYSICALDRIVE5 --bare

cd ~/SonyNasne-debian
lsblk -o NAME,SIZE,FSTYPE,LABEL

NAME     SIZE FSTYPE LABEL
sda    356.9M ext4
sdb    159.4M ext4
sdc     48.8G swap
sdd        1T ext4
sde    931.5G
├─sde1   256M ext3   sys1
├─sde2     1G ext3   sys2
└─sde3 930.3G xfs    user

mkdir -p backup/spi_backup
cp -a /mnt/nasne_sys1/spi_backup/. backup/spi_backup/
cp -r backup/spi_backup /mnt/c/nasne_backup/
sha256sum backup/spi_backup/spi_mtd0.bin /mnt/c/nasne_backup/spi_backup/spi_mtd0.bin

total 16392
drwxr-xr-x 2 root root     1024 Jan  1  1970 .
drwxr-xr-x 6 root root     1024 Jan  1  1970 ..
-rw-r--r-- 1 root root       97 Jan  1  1970 MD5SUMS
-rw-r--r-- 1 root root      440 Jan  1  1970 README.txt
-rw-r--r-- 1 root root      113 Jan  1  1970 SHA1SUMS
-rw-r--r-- 1 root root      500 Jan  1  1970 backup.log
-rw-r--r-- 1 root root 13631488 Jan  1  1970 spi_mtd0.bin
-rw-r--r-- 1 root root  3080192 Jan  1  1970 spi_mtd1_nv.bin
1970-01-01 09:00:27 SPIバックアップ開始 (保存先: sys1)
1970-01-01 09:00:27 mtd0=13631488 mtd1=3080192 (/proc/mtd)
1970-01-01 09:00:27 sys1 をマウント: /dev/sda1 -> /mnt/bk_sys1
1970-01-01 09:00:27 mtd0 を読み出す(2回読んで比較)
208+0 records in
208+0 records out
1970-01-01 09:01:35 mtd0 結果 rc=0
1970-01-01 09:01:35 mtd1(NV領域)を読み出す(稼働中のjffs2なので2回目の比較は参考)
47+0 records in
47+0 records out
1970-01-01 09:01:50 mtd1 結果 rc=0
spi_mtd0.bin: OK
spi_mtd1_nv.bin: OK
spi_mtd0.bin: OK
spi_mtd1_nv.bin: OK

mkdir -p backup/spi_backup
cp -a /mnt/nasne_sys1/spi_backup/. backup/spi_backup/
cp -r backup/spi_backup /mnt/c/nasne_backup/
sha256sum backup/spi_backup/spi_mtd0.bin /mnt/c/nasne_backup/spi_backup/spi_mtd0.bin

6e4f32ddd01dc5019fcca017d2d8cf4eb966fb424121fc792b6b132d9bf180ca  backup/spi_backup/spi_mtd0.bin
6e4f32ddd01dc5019fcca017d2d8cf4eb966fb424121fc792b6b132d9bf180ca  /mnt/c/nasne_backup/spi_backup/spi_mtd0.bin

sudo apt install xfsprogs
sudo xfs_db -r -c "sb 0" -c "print blocksize fdblocks" /dev/sde3

blocksize = 4096
fdblocks = 71878052

sudo xfs_db -r -c "sb 0" -c "print blocksize fdblocks" /dev/sde3 \
  | awk -F' = ' '{v[$1]=$2} END {printf "空き: %.1f GB\n", v["blocksize"]*v["fdblocks"]/1e9}'

空き: 294.4 GB

python3 scripts/nasne_setup.py build --download-official \
  --hdd-dlm backup/00550066.dlm.orig --ssh-pubkey ~/.ssh/nasne_rsa.pub \
  --work build_nasne --telnet fail < /dev/null 2>&1 | tee build2.log

公式rootfs: tar 86026240 bytes、ヘッダ date='Tue Oct 24 11:13:25 2017\x00\x00\x00\x00\x00\x00\x00\x00' +8(major)=2
rcS のエントリ: 2個(最後の #474 を差し替える)
同梱したDebianのエントリ数: 9388
新しいボディ: 93938124 bytes (93.9MB)  公式のエントリ数 1289
/home/xxx/SonyNasne-debian/build_nasne/custom_00550066.dlm: 93938188 bytes  自己検証=OK flag=0 crc=True
読み戻し検証OK: エントリ 10678(元 1289)、rcS 差し替え済み、mode=embed

== ステップ 1: 公式ファームパッケージ
  /home/xxx/SonyNasne-debian/build_nasne/KRST3101_0260_SECURE.dlm (36119466 バイト)

== ステップ 2: カーネルのGPLソース(Sony公開)
  展開済み

== ステップ 3: カーネル用ツールチェーン(Dockerイメージ nasne-kcc:gcc432。gcc 4.3.2 + binutils 2.19.1 をビルド。30分〜1時間)
  イメージあり

== ステップ 4: 自作カーネルのビルド(直起動用の内蔵initramfs入り)
  /home/xxx/SonyNasne-debian/gpl_src/build/out/vmlinux_new.bin あり

== ステップ 5: KNLセグメント(公式のKNLを雛形に、自作カーネルを包む)
  $ /usr/bin/python3 /home/xxx/SonyNasne-debian/scripts/build_knl.py verify /home/xxx/SonyNasne-debian/build_nasne/knl_new.bin

== ステップ 6: Debian wheezy (mipsel) のツリー(debootstrap。数分)
  /home/xxx/SonyNasne-debian/build_nasne/debian_tree.tar あり

== ステップ 7: 00550066.dlm の作成
  $ /usr/bin/python3 /home/xxx/SonyNasne-debian/scripts/stage1/make_stage1_dlm.py build --official /home/xxx/SonyNasne-debian/backup/00550066.dlm.orig --out /home/xxx/SonyNasne-debian/build_nasne/custom_00550066.dlm --mode embed --image-size 8G --telnet fail --debian-tree-tar /home/xxx/SonyNasne-debian/build_nasne/debian_tree.tar

完了: /home/xxx/SonyNasne-debian/build_nasne/custom_00550066.dlm

次はHDDに入れます(HDDをPCにつなぐ。sdX は lsblk で必ず確認):
  sudo mkdir -p /mnt/nasne_sys1 && sudo mount /dev/sdX1 /mnt/nasne_sys1
  mkdir -p backup && cp /mnt/nasne_sys1/00550066.dlm backup/00550066.dlm.orig        # 元に戻す手段
  sudo bash /home/xxx/SonyNasne-debian/scripts/stage1/install_dlm.sh /mnt/nasne_sys1 /home/xxx/SonyNasne-debian/build_nasne/custom_00550066.dlm --backup-dir backup
  sudo umount /mnt/nasne_sys1
その後、HDDを nasne に挿して電源を入れ、約5分待ちます(docs/13)。事前に SPI のバックアップ(docs/16)を取っておくことを強くお勧めします。

df -h /mnt/nasne_sys1

Filesystem      Size  Used Avail Use% Mounted on
/dev/sde1       238M  116M  110M  52% /mnt/nasne_sys1

sudo bash scripts/stage1/install_dlm.sh /mnt/nasne_sys1 build_nasne/custom_00550066.dlm --backup-dir ./backup_sys1_stage2
ls -la /mnt/nasne_sys1
sync
sudo umount /mnt/nasne_sys1

検査OK: hwtype・日付が一致、CRC OK
退避: ./backup_sys1_stage2/00550066.dlm.orig
書き込み完了: /mnt/nasne_sys1/00550066.dlm
/dev/sde1       238M  175M   51M  78% /mnt/nasne_sys1
total 92120
drwxr-xr-x  6 root root     1024 Oct 28 04:05 .
drwxr-xr-x 11 root root     4096 Oct 28 03:57 ..
-rw-r--r--  1 root root      148 Apr 28  2018 00110022.dlm
-rw-r--r--  1 root root 93938188 Oct 28 04:05 00550066.dlm
drwx------  2 root root     1024 Apr 28  2018 11002200
drwx------  2 root root     1024 May 20  2017 33004400
drwx------  2 root root    12288 Jul 26  2013 lost+found
drwxr-xr-x  2 root root     1024 Jan  1  1970 spi_backup

wsl --unmount \\.\PHYSICALDRIVE5

ssh -i ~/.ssh/nasne_rsa -o PubkeyAcceptedAlgorithms=+ssh-rsa -o HostKeyAlgorithms=+ssh-rsa root@192.168.100.xx

The authenticity of host '192.168.100.xx (192.168.100.xx)' can't be established.
ECDSA key fingerprint is: SHA256:v/3+0ie5b0sISn8uV93ZfEmWYAbSZB6TIj6pdWDU26Y
This key is not known by any other names.
Are you sure you want to continue connecting (yes/no/[fingerprint])? 

ssh -i ~/.ssh/nasne_rsa -o PubkeyAcceptedAlgorithms=+ssh-rsa -o HostKeyAlgorithms=+ssh-rsa root@192.168.100.xx

** WARNING: connection is not using a post-quantum key exchange algorithm.
** This session may be vulnerable to "store now, decrypt later" attacks.
** The server may need to be upgraded. See https://openssh.com/pq.html
Linux nasne-debian 2.6.29-ts-mipsisa32r2el #1 Tue Oct 27 17:32:03 UTC 2026 mips

The programs included with the Debian GNU/Linux system are free software;
the exact distribution terms for each program are described in the
individual files in /usr/share/doc/*/copyright.

Debian GNU/Linux comes with ABSOLUTELY NO WARRANTY, to the extent
permitted by applicable law.
root@nasne-debian:~#

uname -a
tail -5 /var/log/nasne-stage1.log
cat /var/log/nasne-mcu-wd.log

root@nasne-debian:~# uname -a
Linux nasne-debian 2.6.29-ts-mipsisa32r2el #1 Tue Oct 27 17:32:03 UTC 2026 mips GNU/Linux

root@nasne-debian:~# tail -5 /var/log/nasne-stage1.log
erased 00100000+00210000
wrote 00207368 bytes at 00100000
verify OK 00207368 bytes at 00100000
1970-01-01 00:03:22 flash + verify OK
1970-01-01 00:03:22 rebooting into the new kernel

root@nasne-debian:~# cat /var/log/nasne-mcu-wd.log
== Thu Jan  1 00:02:09 UTC 1970 start
mcui2c write addr8=20 n=02 ioctl=01 return_value=01 (COMPLETE)
MCU watchdog disabled
mcui2c write addr8=20 n=02 ioctl=01 return_value=01 (COMPLETE)
PWR LED on (code 0x32)
== Thu Jan  1 00:00:19 UTC 1970 start
Found module file xcode4drv.ko
Loaded xcode4 driver module xcode4drv
Created directory /dev/vixs
Created device node /dev/vixs/xcodedrv
Done! Enjoy!
mcui2c write addr8=20 n=02 ioctl=01 return_value=01 (COMPLETE)
MCU watchdog disabled
mcui2c write addr8=20 n=02 ioctl=01 return_value=01 (COMPLETE)
PWR LED on (code 0x32)
root@nasne-debian:~#

http://192.168.100.xx:8301/scan

ch=27 freq=557142kHz sid=0x400(tv) name="NHK総合1・東京" sid=0x401(tv) name="NHK総合2・東京" sid=0x580(1seg) name="NHK携帯G・東京" sid=0xfff0(data)

http://192.168.100.xx:8301/playlist.m3u8

nasne-boot-switch official-once

cd ~/SonyNasne-debian
mkdir -p mirakurun-conf
python3 scripts/nasne_mirakurun_conf.py 192.168.100.xx --scan -o mirakurun-conf
cat mirakurun-conf/channels.yml | head -30

スキャン中(約80秒)...
mirakurun-conf/tuners.yml と channels.yml を書きました(サービス 36 件: GR 36 件, BS 0 件, CS 0 件)

services:
  mirakurun:
    image: chinachu/mirakurun:latest
    container_name: mirakurun
    cap_add:
      - SYS_ADMIN
      - SYS_NICE
    ports:
      - "40772:40772"
    volumes:
      - ./conf:/app-config
      - ./data:/app-data
    environment:
      TZ: Asia/Tokyo
    restart: unless-stopped

// nasne の TS を受け取り、PAT の NIT の PID を 0x10 に直して標準出力へ流す(Mirakurun の tuners.yml から呼ぶ)
// 使い方: node /app-config/nasne-fix.js http://<nasne>:8301/tuner/<channel><sid_query>
// 動作の記録: /app-config/nasne-fix.log(1MBを超えたら作り直す)
const http = require('http');
const fs = require('fs');
const LOG = '/app-config/nasne-fix.log';
const url = process.argv[2];
const t0 = Date.now();
let bytes = 0, pats = 0, fixed = 0, status = '-';
function log(msg) {
  try {
    if (fs.existsSync(LOG) && fs.statSync(LOG).size > 1048576) fs.truncateSync(LOG, 0);
    fs.appendFileSync(LOG, new Date().toISOString() + ' pid=' + process.pid + ' ' + msg + '\n');
  } catch (e) { /* 記録できなくても配信は続ける */ }
}
function finish(code, why) {
  log('exit=' + code + ' reason=' + why + ' status=' + status + ' bytes=' + bytes + ' pats=' + pats + ' fixed=' + fixed + ' ms=' + (Date.now() - t0) + ' url=' + url);
  process.exit(code);
}
const T = new Uint32Array(256);
for (let i = 0; i < 256; i++) { let c = i << 24; for (let k = 0; k < 8; k++) c = (c & 0x80000000) ? ((c << 1) ^ 0x04C11DB7) : (c << 1); T[i] = c >>> 0; }
function crc32(b, s, e) { let c = 0xFFFFFFFF; for (let i = s; i < e; i++) c = ((c << 8) ^ T[((c >>> 24) ^ b[i]) & 0xff]) >>> 0; return c >>> 0; }
function fix(p) {
  if (p[0] !== 0x47 || (p[1] & 0x1f) !== 0 || p[2] !== 0 || !(p[1] & 0x40) || !(p[3] & 0x10)) return;
  let off = 4; if (p[3] & 0x20) off += 1 + p[4];
  off += 1 + p[off];
  if (off + 8 > 188 || p[off] !== 0x00) return;
  const end = off + 3 + (((p[off + 1] & 0x0f) << 8) | p[off + 2]);
  if (end > 188) return;
  pats++;
  let changed = false;
  for (let j = off + 8; j + 4 <= end - 4; j += 4) {
    if (p[j] === 0 && p[j + 1] === 0 && (((p[j + 2] & 0x1f) << 8) | p[j + 3]) !== 0x10) {
      p[j + 2] = 0xe0; p[j + 3] = 0x10; changed = true;
    }
  }
  if (changed) { p.writeUInt32BE(crc32(p, off, end - 4), end - 4); fixed++; }
}
module.exports = { fix, crc32 };
if (require.main === module) {
  process.on('SIGTERM', () => finish(0, 'SIGTERM(Mirakurunが終了を指示)'));
  process.on('uncaughtException', e => finish(1, 'exception:' + (e && e.stack || e)));
  process.stdout.on('error', e => finish(0, 'stdout-error:' + e.code));
  let rest = Buffer.alloc(0);
  log('start url=' + url);
  const req = http.get(url, res => {
    status = String(res.statusCode);
    if (res.statusCode !== 200) {
      let body = '';
      res.on('data', d => { if (body.length < 200) body += d.toString(); });
      res.on('end', () => finish(1, 'http-status body=' + JSON.stringify(body.trim())));
      return;
    }
    res.on('data', chunk => {
      bytes += chunk.length;
      const buf = rest.length ? Buffer.concat([rest, chunk]) : chunk;
      let i = 0; while (i < buf.length && buf[i] !== 0x47) i++;
      const n = Math.floor((buf.length - i) / 188) * 188;
      for (let k = i; k < i + n; k += 188) fix(buf.subarray(k, k + 188));
      if (n) process.stdout.write(buf.subarray(i, i + n));
      rest = Buffer.from(buf.subarray(i + n));
    });
    res.on('end', () => finish(0, 'stream-end'));
    res.on('aborted', () => finish(1, 'stream-aborted'));
  });
  req.on('error', e => finish(1, 'request-error:' + e.code + ' ' + e.message));
}

- name: nasne
  types:
    - GR
  command: node /app-config/nasne-fix.js http://192.168.100.xxx:8301/tuner/<channel><sid_query>
  isDisabled: false

mkdir -p ~/epgstation-config && cd ~/epgstation-config
docker create --name tmp-epg l3tnun/epgstation:master-debian
docker cp tmp-epg:/app/config/. . && docker rm tmp-epg
cp config.yml.template config.yml && cp enc.js.template enc.js
cp operatorLogConfig.sample.yml operatorLogConfig.yml
cp serviceLogConfig.sample.yml serviceLogConfig.yml
cp epgUpdaterLogConfig.sample.yml epgUpdaterLogConfig.yml
sed -i 's#^mirakurunPath:.*#mirakurunPath: http://mirakurun:40772/#' config.yml
grep mirakurunPath config.yml

mirakurunPath: http://mirakurun:40772/

FROM l3tnun/epgstation:master-debian
RUN apt-get update \
 && apt-get install -y --no-install-recommends ffmpeg \
 && ln -sf /usr/bin/ffmpeg /usr/local/bin/ffmpeg \
 && ln -sf /usr/bin/ffprobe /usr/local/bin/ffprobe \
 && rm -rf /var/lib/apt/lists/*

services:
  mirakurun:
    image: chinachu/mirakurun:latest
    container_name: mirakurun
    cap_add:
      - SYS_ADMIN
      - SYS_NICE
    ports:
      - "40772:40772"
    volumes:
      - ./conf:/app-config
      - ./data:/app-data
    environment:
      TZ: Asia/Tokyo
    restart: unless-stopped

  epgstation:
    build: ./epgstation-build
    image: epgstation-ffmpeg:local
    container_name: epgstation
    ports:
      - "8888:8888"
    volumes:
      - ./epgstation/config:/app/config
      - ./epgstation/data:/app/data
      - ./epgstation/recorded:/app/recorded
      - ./epgstation/thumbnail:/app/thumbnail
      - ./epgstation/logs:/app/logs
    environment:
      TZ: Asia/Tokyo
    depends_on:
      - mirakurun
    restart: unless-stopped

g = nx.DiGraph()
g.add_node("code_atlas.llm:LLMClient.chat")              # 点を追加
g.add_edge("code_atlas.llm:LLMClient.test_connection",   # 矢印を追加
           "code_atlas.llm:LLMClient.chat")

ollama show gpt-oss:20b --modelfile > official-gpt-oss.Modelfile

# Modelfile generated by "ollama show"
# To build a new Modelfile based on this, replace FROM with:
# FROM gpt-oss:20b

FROM G:\ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb
TEMPLATE """<|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: {{ currentDate }}
{{- if and .IsThinkSet .Think (ne .ThinkLevel "") }}

Reasoning: {{ .ThinkLevel }}
{{- else if or (not .IsThinkSet) (and .IsThinkSet .Think) }}

Reasoning: medium
{{- end }}

{{- $hasNonBuiltinTools := false }}
{{- if .Tools -}}
{{- $hasBrowserSearch := false }}
{{- $hasBrowserOpen := false }}
{{- $hasBrowserFind := false }}
{{- $hasPython := false }}
  {{- range .Tools }}
    {{- if eq .Function.Name "browser.search" -}}{{- $hasBrowserSearch = true -}}
    {{- else if eq .Function.Name "browser.open" -}}{{- $hasBrowserOpen = true -}}
    {{- else if eq .Function.Name "browser.find" -}}{{- $hasBrowserFind = true -}}
    {{- else if eq .Function.Name "python" -}}{{- $hasPython = true -}}
    {{- else }}{{ $hasNonBuiltinTools = true -}}
    {{- end }}
  {{- end }}
{{- if or $hasBrowserSearch $hasBrowserOpen $hasBrowserFind $hasPython }}

# Tools
{{- if or $hasBrowserSearch $hasBrowserOpen $hasBrowserFind }}

## browser

// Tool for browsing.
// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.
// Cite information from the tool using the following format:
// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.
// Do not quote more than 10 words directly from the tool output.
// sources=web (default: web)
namespace browser {
{{- if $hasBrowserSearch }}

// Searches for information related to `query` and displays `topn` results.
type search = (_: {
query: string,
topn?: number, // default: 10
source?: string,
}) => any;
{{- end }}
{{- if $hasBrowserOpen }}

// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.
// Valid link ids are displayed with the formatting: `【{id}†.*】`.
// If `cursor` is not provided, the most recent page is implied.
// If `id` is a string, it is treated as a fully qualified URL associated with `source`.
// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.
// Use this function without `id` to scroll to a new location of an opened page.
type open = (_: {
id?: number | string, // default: -1
cursor?: number, // default: -1
loc?: number, // default: -1
num_lines?: number, // default: -1
view_source?: boolean, // default: false
source?: string,
}) => any;
{{- end }}
{{- if $hasBrowserFind }}

// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.
type find = (_: {
pattern: string,
cursor?: number, // default: -1
}) => any;
{{- end }}

} // namespace browser
{{- end }}{{/* end if has browser tools */}}
{{- if $hasPython }}

## python

Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).

When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.
{{- end }}{{/* end if hasPython */}}
{{- end }}{{/* end if has any built-in tools */}}
{{- end }}{{/* end if .Tools */}}

# Valid channels: analysis, commentary, final. Channel must be included for every message.{{ if $hasNonBuiltinTools }}
Calls to these tools must go to the commentary channel: 'functions'.
{{- end -}}<|end|>{{/* end of system */ -}}
{{- if or $hasNonBuiltinTools .System -}}
<|start|>developer<|message|>{{- if $hasNonBuiltinTools }}# Tools

## functions

namespace functions {
{{- range .Tools }}
{{- if not (or (eq .Function.Name "browser.search") (eq .Function.Name "browser.open") (eq .Function.Name "browser.find") (eq .Function.Name "python")) }}
{{if .Function.Description }}
// {{ .Function.Description }}
{{- end }}
{{- if and .Function.Parameters.Properties (gt (len .Function.Parameters.Properties) 0) }}
type {{ .Function.Name }} = (_: {
{{- range $name, $prop := .Function.Parameters.Properties }}
{{- if $prop.Description }}
  // {{ $prop.Description }}
{{- end }}
  {{ $name }}: {{ $prop | toTypeScriptType }},
{{- end }}
}) => any;
{{- else }}
type {{ .Function.Name }} = () => any;
{{- end }}
{{- end }}{{/* end if not browser tool */}}
{{- end }}{{/* end of range .Tools */}}

} // namespace functions
{{- end }}{{/* end if hasNonBuiltinTools */}}
{{- if .System}}

# Instructions

{{ .System }}
{{- end -}}
<|end|>
{{- end -}}
{{- /* Find the index of the last user message */ -}}
{{- $lastUserIdx := -1 }}
{{- $prefillingContent := false }}
{{- $prefillingThinkingOnly := false }}
{{- range $i, $msg := .Messages }}
  {{- $last := eq (len (slice $.Messages $i)) 1 -}}
  {{- if eq $msg.Role "user" }}
    {{- $lastUserIdx = $i }}
  {{- end -}}
  {{- if and $last (eq $msg.Role "assistant") (gt (len $msg.Content) 0) }}
    {{- $prefillingContent = true }}
  {{- else if and $last (eq $msg.Role "assistant") (gt (len $msg.Thinking) 0) }}
    {{- $prefillingThinkingOnly = true }}
  {{- end }}
{{- end -}}
{{- /* Now render messages */ -}}
{{- range $i, $msg := .Messages }}
  {{- $last := eq (len (slice $.Messages $i)) 1 -}}
  {{- if (ne $msg.Role "system") -}}
    {{- if eq $msg.Role "tool" -}}
      {{- if or (eq $msg.ToolName "python") (eq $msg.ToolName "browser.search") (eq $msg.ToolName "browser.open") (eq $msg.ToolName "browser.find") -}}
        <|start|>{{ $msg.ToolName }} to=assistant<|message|>{{ $msg.Content }}<|end|>
      {{- else -}}
        <|start|>functions.{{ $msg.ToolName }} to=assistant<|message|>{{ $msg.Content }}<|end|>
      {{- end -}}
    {{- else if eq $msg.Role "assistant" -}}
      {{- if and $msg.Thinking (gt $i $lastUserIdx) -}}{{- /* Show thinking only after last user message */ -}}
      <|start|>assistant<|channel|>analysis<|message|>{{ $msg.Thinking }}{{- if not $prefillingThinkingOnly -}}<|end|>{{- end -}}
      {{- end -}}
      {{- if gt (len $msg.Content) 0 -}}
        <|start|>assistant<|channel|>final<|message|>{{ $msg.Content }}{{- if not $prefillingContent -}}<|end|>{{- end -}}
      {{- end -}}
      {{- if gt (len $msg.ToolCalls) 0 -}}
        {{- range $j, $toolCall := $msg.ToolCalls -}}
          {{- $isBuiltin := or (eq $toolCall.Function.Name "python") (eq $toolCall.Function.Name "browser.search") (eq $toolCall.Function.Name "browser.open") (eq $toolCall.Function.Name "browser.find") -}}
          <|start|>assistant<|channel|>{{ if $isBuiltin }}analysis{{ else }}commentary{{ end }} to={{ if not $isBuiltin}}functions.{{end}}{{ $toolCall.Function.Name }} <|constrain|>json<|message|>{{ $toolCall.Function.Arguments }}<|call|>
        {{- end -}}
      {{- end -}}
    {{- else if eq $msg.Role "user" -}}
      <|start|>{{ $msg.Role }}<|message|>{{ $msg.Content }}<|end|>
    {{- end }}
  {{- else }}
  {{- end }}
{{- end -}}
{{- if not (or $prefillingContent $prefillingThinkingOnly) -}}
<|start|>assistant
{{- end -}}"""
PARAMETER temperature 1
LICENSE """
                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.

      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the
      direction or management of such entity, whether by contract or
      otherwise, or (ii) ownership of fifty percent (50%) or more of the
      outstanding shares, or (iii) beneficial ownership of such entity.

      "You" (or "Your") shall mean an individual or Legal Entity
      exercising permissions granted by this License.

      "Source" form shall mean the preferred form for making modifications,
      including but not limited to software source code, documentation
      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions
      to that Work or Derivative Works thereof, that is intentionally
      submitted to Licensor for inclusion in the Work by the copyright owner
      or by an individual or Legal Entity authorized to submit on behalf of
      the copyright owner. For the purposes of this definition, "submitted"
      means any form of electronic, verbal, or written communication sent
      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise
      designated in writing by the copyright owner as "Not a Contribution."

      "Contributor" shall mean Licensor and any individual or Legal Entity
      on behalf of whom a Contribution has been received by Licensor and
      subsequently incorporated within the Work.

   2. Grant of Copyright License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      copyright license to reproduce, prepare Derivative Works of,
      publicly display, publicly perform, sublicense, and distribute the
      Work and such Derivative Works in Source or Object form.

   3. Grant of Patent License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      (except as stated in this section) patent license to make, have made,
      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a
      cross-claim or counterclaim in a lawsuit) alleging that the Work
      or a Contribution incorporated within the Work constitutes direct
      or contributory patent infringement, then any patent licenses
      granted to You under this License for that Work shall terminate
      as of the date such litigation is filed.

   4. Redistribution. You may reproduce and distribute copies of the
      Work or Derivative Works thereof in any medium, with or without
      modifications, and in Source or Object form, provided that You
      meet the following conditions:

      (a) You must give any other recipients of the Work or
          Derivative Works a copy of this License; and

      (b) You must cause any modified files to carry prominent notices
          stating that You changed the files; and

      (c) You must retain, in the Source form of any Derivative Works
          that You distribute, all copyright, patent, trademark, and
          attribution notices from the Source form of the Work,
          excluding those notices that do not pertain to any part of
          the Derivative Works; and

      (d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,
          within a display generated by the Derivative Works, if and
          wherever such third-party notices normally appear. The contents
          of the NOTICE file are for informational purposes only and
          do not modify the License. You may add Your own attribution
          notices within Derivative Works that You distribute, alongside
          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.

      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or
      for any such Derivative Works as a whole, provided Your use,
      reproduction, and distribution of the Work otherwise complies with
      the conditions stated in this License.

   5. Submission of Contributions. Unless You explicitly state otherwise,
      any Contribution intentionally submitted for inclusion in the Work
      by You to the Licensor shall be under the terms and conditions of
      this License, without any additional terms or conditions.
      Notwithstanding the above, nothing herein shall supersede or modify
      the terms of any separate license agreement you may have executed
      with Licensor regarding such Contributions.

   6. Trademarks. This License does not grant permission to use the trade
      names, trademarks, service marks, or product names of the Licensor,
      except as required for reasonable and customary use in describing the
      origin of the Work and reproducing the content of the NOTICE file.

   7. Disclaimer of Warranty. Unless required by applicable law or
      agreed to in writing, Licensor provides the Work (and each
      Contributor provides its Contributions) on an "AS IS" BASIS,
      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
      implied, including, without limitation, any warranties or conditions
      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,
      whether in tort (including negligence), contract, or otherwise,
      unless required by applicable law (such as deliberate and grossly
      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all
      other commercial damages or losses), even if such Contributor
      has been advised of the possibility of such damages.

   9. Accepting Warranty or Additional Liability. While redistributing
      the Work or Derivative Works thereof, You may choose to offer,
      and charge a fee for, acceptance of support, warranty, indemnity,
      or other liability obligations and/or rights consistent with this
      License. However, in accepting such obligations, You may act only
      on Your own behalf and on Your sole responsibility, not on behalf
      of any other Contributor, and only if You agree to indemnify,
      defend, and hold each Contributor harmless for any liability
      incurred by, or claims asserted against, such Contributor by reason
      of your accepting any such warranty or additional liability.

   END OF TERMS AND CONDITIONS

   APPENDIX: How to apply the Apache License to your work.

      To apply the Apache License to your work, attach the following
      boilerplate notice, with the fields enclosed by brackets "[]"
      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.
   Copyright [yyyy] [name of copyright owner]
   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.
   You may obtain a copy of the License at
       http://www.apache.org/licenses/LICENSE-2.0
   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License."""

conda create -n presidio_20260831 python==3.13

pip install "presidio_analyzer[transformers]"

pip install attrs tenacity sniffio requests-toolbelt distro zstandard jsonpatch mypy-extensions --upgrade

pip install  cryptography  marshmallow==3.26.2 referencing

pip install presidio_anonymizer

python -m spacy download en_core_web_sm

pip install presidio_image_redactor

pip install jupyterlab ipywidgets

text = "私は田中太郎。住所は279-0031 千葉県浦安市舞浜１−１。電話番号は03-999-9999。マイナンバーは123456789012。"

from presidio_analyzer import AnalyzerEngine
from presidio_analyzer.nlp_engine import TransformersNlpEngine
from presidio_anonymizer import AnonymizerEngine

model_config = [{"lang_code": "en", "model_name": {
    "spacy": "en_core_web_sm",  # use a small spaCy model for lemmas, tokens etc.
    "transformers": r"H:\BERT_Models\dslim\bert-base-NER"
    }
}]

nlp_engine = TransformersNlpEngine(models=model_config)
analyzer = AnalyzerEngine(nlp_engine=nlp_engine)

results = analyzer.analyze(text=text, language='en')
print(results)

anonymizer = AnonymizerEngine()
anonymized_text = anonymizer.anonymize(text=text, analyzer_results=results)

print(anonymized_text)

Some weights of the model checkpoint at H:\BERT_Models\dslim\bert-base-NER were not used when initializing BertForTokenClassification: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight']
- This IS expected if you are initializing BertForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing BertForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Device set to use cpu
[type: PHONE_NUMBER, start: 36, end: 47, score: 0.4]
text: 私は田中太郎。住所は279-0031 千葉県浦安市舞浜１−１。電話番号は<PHONE_NUMBER>。マイナンバーは123456789012。
items:
[
    {'start': 36, 'end': 50, 'entity_type': 'PHONE_NUMBER', 'text': '<PHONE_NUMBER>', 'operator': 'replace'}
]

python -m spacy download ja_core_news_sm

model_config = [{"lang_code": "ja", "model_name": {
    "spacy": "ja_core_news_sm",
    "transformers": r"H:\BERT_Models\tsmatz\xlm-roberta-ner-japanese"
    }
}]

nlp_engine = TransformersNlpEngine(models=model_config)
analyzer = AnalyzerEngine(nlp_engine=nlp_engine)

results = analyzer.analyze(text=text, language='ja')
print(results)

anonymizer = AnonymizerEngine()
anonymized_text = anonymizer.anonymize(text=text, analyzer_results=results)

print(anonymized_text)

Device set to use cpu
[type: LOCATION, start: 19, end: 21, score: 0.9985260963439941]
text: 私は田中太郎。住所は279-0031 <LOCATION>県浦安市舞浜１−１。電話番号は03-999-9999。マイナンバーは123456789012。
items:
[
    {'start': 19, 'end': 29, 'entity_type': 'LOCATION', 'text': '<LOCATION>', 'operator': 'replace'}
]

c:\ProgramData\anaconda3\envs\presidio_20260831\Lib\site-packages\transformers\pipelines\token_classification.py:490: UserWarning: Tokenizer does not support real words, using fallback heuristic
  warnings.warn(

pip install -U ginza ja_ginza

import spacy
import ginza

# GiNZAのcompound_splitterはsplit_mode未指定だとエラーになるため、
# spacy.load を一時的にラップしてconfigを注入する
_original_spacy_load = spacy.load

def _patched_spacy_load(name, *args, **kwargs):
    if name == "ja_ginza" and "config" not in kwargs:
        kwargs["config"] = {"components": {"compound_splitter": {"split_mode": "A"}}}
    return _original_spacy_load(name, *args, **kwargs)

spacy.load = _patched_spacy_load


from presidio_analyzer import AnalyzerEngine
from presidio_analyzer.nlp_engine import TransformersNlpEngine
from presidio_anonymizer import AnonymizerEngine

model_config = [{"lang_code": "ja", "model_name": {
    "spacy": "ja_ginza",  # ← ja_core_news_sm から変更
    "transformers": r"H:\BERT_Models\tsmatz\xlm-roberta-ner-japanese"
    }
}]

nlp_engine = TransformersNlpEngine(models=model_config)
analyzer = AnalyzerEngine(nlp_engine=nlp_engine)

results = analyzer.analyze(text=text, language='ja')
print(results)

anonymizer = AnonymizerEngine()
anonymized_text = anonymizer.anonymize(text=text, analyzer_results=results)

print(anonymized_text)

Device set to use cpu
[type: LOCATION, start: 19, end: 27, score: 0.9985260963439941]
text: 私は田中太郎。住所は279-0031 <LOCATION>１−１。電話番号は03-999-9999。マイナンバーは123456789012。
items:
[
    {'start': 19, 'end': 29, 'entity_type': 'LOCATION', 'text': '<LOCATION>', 'operator': 'replace'}
]

c:\ProgramData\anaconda3\envs\presidio_20260831\Lib\site-packages\transformers\pipelines\token_classification.py:490: UserWarning: Tokenizer does not support real words, using fallback heuristic
  warnings.warn(

import spacy
import ginza

if not getattr(spacy.load, "_ja_ginza_patched", False):
    _original_spacy_load = spacy.load

    def _make_patched_load(original_load):
        def _patched(name, *args, **kwargs):
            if name == "ja_ginza":
                # "disable" は生成はするが実行しないだけなので、
                # compound_splitter の split_mode 検証エラーを避けられない。
                # "exclude" ならコンポーネント自体を生成しないため、この問題を回避できる。
                exclude = list(kwargs.get("exclude", []))
                for comp in ("compound_splitter", "bunsetu_recognizer"):
                    if comp not in exclude:
                        exclude.append(comp)
                kwargs["exclude"] = exclude
                kwargs.pop("config", None)
            return original_load(name, *args, **kwargs)
        _patched._ja_ginza_patched = True
        return _patched

    spacy.load = _make_patched_load(_original_spacy_load)

from presidio_analyzer import AnalyzerEngine, Pattern, PatternRecognizer, RecognizerRegistry
from presidio_analyzer.nlp_engine import TransformersNlpEngine, NerModelConfiguration
from presidio_anonymizer import AnonymizerEngine


# ============================================================
# NLPエンジン設定(GiNZA + xlm-roberta-ner-japanese)
# ============================================================
model_config = [{"lang_code": "ja", "model_name": {
    "spacy": "ja_ginza",
    "transformers": r"H:\BERT_Models\tsmatz\xlm-roberta-ner-japanese"
    }
}]

ner_model_configuration = NerModelConfiguration(
    model_to_presidio_entity_mapping={
        "PER": "PERSON",
        "PERSON": "PERSON",
        "LOC": "LOCATION",
        "GPE": "LOCATION",
        "ORG": "ORGANIZATION",
        "DAT": "DATE_TIME",
        "DATE": "DATE_TIME",
        "TIM": "DATE_TIME",
        "TIME": "DATE_TIME",
        "MONEY": "MONEY",
        "PERCENT": "PERCENT",
    },
    low_confidence_score_multiplier=0.4,
    low_score_entity_names=["ORGANIZATION"],
    alignment_mode="expand",
    aggregation_strategy="simple",  # 日本語(スペース無し)では"average"等だと、空白ベースのフォールバック判定が誤動作するため"simple"を使う
)

nlp_engine = TransformersNlpEngine(
    models=model_config,
    ner_model_configuration=ner_model_configuration,
)
nlp_engine.load()


# ============================================================
# カスタムレコグナイザー: 郵便番号・マイナンバー
# ============================================================
postal_recognizer = PatternRecognizer(
    supported_entity="JP_POSTAL_CODE",
    patterns=[Pattern(name="jp_postal_code", regex=r"\b\d{3}-\d{4}\b", score=0.85)],
    context=["郵便番号", "〒"],
    supported_language="ja",
)

my_number_recognizer = PatternRecognizer(
    supported_entity="JP_MY_NUMBER",
    patterns=[Pattern(name="jp_my_number", regex=r"(?<!\d)\d{12}(?!\d)", score=0.3)],
    context=["マイナンバー", "個人番号"],
    supported_language="ja",
)


# ============================================================
# レジストリ構築(既定 + カスタムを統合)
# ============================================================
registry = RecognizerRegistry(supported_languages=["ja"])
registry.load_predefined_recognizers(nlp_engine=nlp_engine, languages=["ja"])
registry.add_recognizer(postal_recognizer)
registry.add_recognizer(my_number_recognizer)

analyzer = AnalyzerEngine(
    nlp_engine=nlp_engine,
    registry=registry,
    supported_languages=["ja"],
)


# ============================================================
# 実行
# ============================================================
results = analyzer.analyze(text=text, language='ja')
print(results)

anonymizer = AnonymizerEngine()
anonymized_text = anonymizer.anonymize(text=text, analyzer_results=results)

print(anonymized_text)

Device set to use cpu
[type: PERSON, start: 2, end: 6, score: 0.999563992023468, type: LOCATION, start: 10, end: 30, score: 0.998464047908783, type: JP_POSTAL_CODE, start: 39, end: 47, score: 0.85, type: JP_MY_NUMBER, start: 55, end: 67, score: 0.6499999999999999, type: PHONE_NUMBER, start: 36, end: 47, score: 0.4]
text: 私は<PERSON>。住所は<LOCATION>。電話番号は<PHONE_NUMBER>。マイナンバーは<JP_MY_NUMBER>。
items:
[
    {'start': 52, 'end': 66, 'entity_type': 'JP_MY_NUMBER', 'text': '<JP_MY_NUMBER>', 'operator': 'replace'},
    {'start': 30, 'end': 44, 'entity_type': 'PHONE_NUMBER', 'text': '<PHONE_NUMBER>', 'operator': 'replace'},
    {'start': 14, 'end': 24, 'entity_type': 'LOCATION', 'text': '<LOCATION>', 'operator': 'replace'},
    {'start': 2, 'end': 10, 'entity_type': 'PERSON', 'text': '<PERSON>', 'operator': 'replace'}
]

import pytesseract
from presidio_image_redactor import ImageRedactorEngine
from PIL import Image

pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"

image = Image.open(r"D:\Workspace\Python\Presidio\pii_test_document.png")

redactor = ImageRedactorEngine()
redacted_image = redactor.redact(image=image, ocr_kwargs={"lang": "jpn"})

# オリジナル表示
display(image)
display(redacted_image)

import spacy
import ginza

if not getattr(spacy.load, "_ja_ginza_patched", False):
    _original_spacy_load = spacy.load

    def _make_patched_load(original_load):
        def _patched(name, *args, **kwargs):
            if name == "ja_ginza":
                exclude = list(kwargs.get("exclude", []))
                for comp in ("compound_splitter", "bunsetu_recognizer"):
                    if comp not in exclude:
                        exclude.append(comp)
                kwargs["exclude"] = exclude
                kwargs.pop("config", None)
            return original_load(name, *args, **kwargs)
        _patched._ja_ginza_patched = True
        return _patched

    spacy.load = _make_patched_load(_original_spacy_load)


from presidio_analyzer import AnalyzerEngine, Pattern, PatternRecognizer, RecognizerRegistry
from presidio_analyzer.nlp_engine import TransformersNlpEngine, NerModelConfiguration
from presidio_image_redactor import ImageRedactorEngine, ImageAnalyzerEngine
import pytesseract
from PIL import Image

pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"


# ============================================================
# 日本語NLPエンジン(GiNZA + xlm-roberta-ner-japanese)
# ============================================================
model_config = [{"lang_code": "ja", "model_name": {
    "spacy": "ja_ginza",
    "transformers": r"H:\BERT_Models\tsmatz\xlm-roberta-ner-japanese"
    }
}]

ner_model_configuration = NerModelConfiguration(
    model_to_presidio_entity_mapping={
        "PER": "PERSON", "PERSON": "PERSON",
        "LOC": "LOCATION", "GPE": "LOCATION",
        "ORG": "ORGANIZATION",
        "DAT": "DATE_TIME", "DATE": "DATE_TIME",
        "TIM": "DATE_TIME", "TIME": "DATE_TIME",
        "MONEY": "MONEY", "PERCENT": "PERCENT",
    },
    low_confidence_score_multiplier=0.4,
    low_score_entity_names=["ORGANIZATION"],
    alignment_mode="expand",
    aggregation_strategy="simple",
)

nlp_engine = TransformersNlpEngine(models=model_config, ner_model_configuration=ner_model_configuration)
nlp_engine.load()


# ============================================================
# カスタムレコグナイザー(郵便番号・マイナンバー)
# ============================================================
postal_recognizer = PatternRecognizer(
    supported_entity="JP_POSTAL_CODE",
    patterns=[Pattern(name="jp_postal_code", regex=r"\b\d{3}-\d{4}\b", score=0.85)],
    context=["郵便番号", "〒"],
    supported_language="ja",
)
my_number_recognizer = PatternRecognizer(
    supported_entity="JP_MY_NUMBER",
    patterns=[Pattern(name="jp_my_number", regex=r"(?<!\d)\d{12}(?!\d)", score=0.3)],
    context=["マイナンバー", "個人番号"],
    supported_language="ja",
)

registry = RecognizerRegistry(supported_languages=["ja"])
registry.load_predefined_recognizers(nlp_engine=nlp_engine, languages=["ja"])
registry.add_recognizer(postal_recognizer)
registry.add_recognizer(my_number_recognizer)

analyzer = AnalyzerEngine(nlp_engine=nlp_engine, registry=registry, supported_languages=["ja"])


# ============================================================
# 画像レダクター: 日本語analyzerを明示的に組み込む
# ============================================================
image_analyzer_engine = ImageAnalyzerEngine(analyzer_engine=analyzer)
redactor = ImageRedactorEngine(image_analyzer_engine=image_analyzer_engine)

image = Image.open(r"D:\Workspace\Python\Presidio\pii_test_document.png")

redacted_image = redactor.redact(
    image=image,
    ocr_kwargs={"lang": "jpn"},
    language="ja",
)

redacted_image