From 00b267b651634f66a705095b97b739f0d9b9082a Mon Sep 17 00:00:00 2001 From: sophon Date: Fri, 9 Jan 2026 11:29:25 +0800 Subject: [PATCH 1/3] modify scripts --- docker/stash/scripts/video_merge.sh | 125 ---------------------------- 1 file changed, 125 deletions(-) delete mode 100644 docker/stash/scripts/video_merge.sh diff --git a/docker/stash/scripts/video_merge.sh b/docker/stash/scripts/video_merge.sh deleted file mode 100644 index 89606a4..0000000 --- a/docker/stash/scripts/video_merge.sh +++ /dev/null @@ -1,125 +0,0 @@ -#!/bin/bash -# 功能：绿联NAS通用视频无损合并脚本（自动识别格式） -# 支持格式：MP4、AVI、WMV -# 使用要求：所有输入文件格式必须一致，最后一个参数为输出文件名 -# 使用方法：./merge_video_unified.sh 1.mp4 2.mp4 merged.mp4（或avi/wmv格式） - -# 定义颜色输出 -RED='\033[0;31m' -GREEN='\033[0;32m' -YELLOW='\033[1;33m' -NC='\033[0m' # 恢复默认颜色 - -# 初始化变量 -input_files=() -output_file="" -file_list="tmp_video_list.txt" -detected_format="" -supported_formats=("mp4" "avi" "wmv") # 支持的格式列表 - -# -------------------------- 步骤1：解析与校验参数 -------------------------- -# 1. 校验参数数量（至少2个输入+1个输出） -if [[ $# -lt 3 ]]; then - echo -e "${RED}错误：参数数量不足！格式：脚本名 输入1 输入2 ... 输出文件${NC}" - echo -e "${YELLOW}使用示例：${NC}" - echo -e " MP4：./merge_video_unified.sh 1.mp4 2.mp4 merged.mp4" - echo -e " AVI：./merge_video_unified.sh 1.avi 2.avi merged.avi" - echo -e " WMV：./merge_video_unified.sh 1.wmv 2.wmv merged.wmv" - exit 1 -fi - -# 2. 提取输出文件（最后一个参数）和输入文件（前面所有参数） -output_file="${!#}" -input_files=("${@:1:$#-1}") - -# -------------------------- 步骤2：检测并校验输入文件格式 -------------------------- -# 1. 检测第一个输入文件的格式 -first_file="${input_files[0]}" -# 提取文件后缀（忽略大小写） -file_suffix=$(echo "$first_file" | awk -F '.' '{print tolower($NF)}') - -# 2. 校验是否为支持的格式 -if [[ ! " ${supported_formats[@]} " =~ " ${file_suffix} " ]]; then - echo -e "${RED}错误：不支持该格式！仅支持：${supported_formats[*]}${NC}" - exit 1 -fi -detected_format="$file_suffix" -echo -e "${GREEN}已检测到输入文件格式：$detected_format${NC}" - -# 3. 校验所有输入文件格式是否一致 -for file in "${input_files[@]}"; do - # 检查文件是否存在 - if [[ ! -f "$file" ]]; then - echo -e "${RED}错误：输入文件 $file 不存在！${NC}" - exit 1 - fi - # 提取当前文件后缀 - current_suffix=$(echo "$file" | awk -F '.' '{print tolower($NF)}') - # 对比格式是否一致 - if [[ "$current_suffix" != "$detected_format" ]]; then - echo -e "${RED}错误：输入文件格式不一致！$file 不是 $detected_format 格式${NC}" - exit 1 - fi -done - -# -------------------------- 步骤3：处理输出文件 -------------------------- -# 1. 自动补全输出文件后缀 -output_suffix=$(echo "$output_file" | awk -F '.' '{print tolower($NF)}') -if [[ "$output_suffix" != "$detected_format" ]]; then - output_file="${output_file}.${detected_format}" - echo -e "${YELLOW}提示：输出文件已自动补全为 ${detected_format} 格式：$output_file${NC}" -fi - -# 2. 输出文件覆盖提示 -if [[ -f "$output_file" ]]; then - read -p "提示：输出文件 $output_file 已存在，是否覆盖？(y/n) " choice - case "$choice" in - y|Y) echo -e "${YELLOW}即将覆盖输出文件 $output_file${NC}" ;; - *) echo -e "${GREEN}操作已取消${NC}"; exit 0 ;; - esac -fi - -# -------------------------- 步骤4：校验ffmpeg -------------------------- -if ! command -v ffmpeg &> /dev/null; then - echo -e "${RED}错误：未检测到ffmpeg，请先安装！${NC}" - exit 1 -fi - -# -------------------------- 步骤5：执行合并 -------------------------- -echo -e "${GREEN}=====================================${NC}" -echo -e "${GREEN}开始执行 ${detected_format} 格式无损合并${NC}" -echo -e "${GREEN}待合并文件（传入顺序）：${NC}" -for i in "${!input_files[@]}"; do - echo " $((i+1)). ${input_files[$i]}" -done -echo -e "${GREEN}输出文件：$output_file${NC}" -echo -e "${GREEN}=====================================${NC}" - -# 1. 生成临时文件列表 -echo -e "${YELLOW}正在生成临时文件列表...${NC}" -> "$file_list" # 清空临时文件 -for file in "${input_files[@]}"; do - abs_file=$(realpath "$file") - echo "file '$abs_file'" >> "$file_list" -done -echo -e "${GREEN}临时文件列表生成完成：$file_list${NC}" - -# 2. 执行ffmpeg合并 -echo -e "${YELLOW}正在合并 ${detected_format} 文件（无损拷贝，耗时取决于文件大小）...${NC}" -ffmpeg -f concat -safe 0 -i "$file_list" -c copy -y "$output_file" - -# -------------------------- 步骤6：结果判断与清理 -------------------------- -if [[ $? -eq 0 ]]; then - echo -e "${GREEN}=====================================${NC}" - echo -e "${GREEN}${detected_format} 格式合并成功！输出文件：$output_file${NC}" - rm -f "$file_list" - echo -e "${GREEN}临时文件 $file_list 已清理${NC}" - echo -e "${GREEN}=====================================${NC}" -else - echo -e "${RED}=====================================${NC}" - echo -e "${RED}${detected_format} 格式合并失败！请确认所有文件编码/分辨率/帧率一致${NC}" - rm -f "$file_list" - echo -e "${RED}临时文件 $file_list 已清理${NC}" - echo -e "${RED}=====================================${NC}" - exit 1 -fi \ No newline at end of file From dece263c8b596fc89f7f36c86c6cea299e02f8f4 Mon Sep 17 00:00:00 2001 From: sophon Date: Sun, 11 Jan 2026 10:36:07 +0800 Subject: [PATCH 2/3] modify scripts --- docker/paperless/plugins/{consume.sh => em_reports_consume.sh} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename docker/paperless/plugins/{consume.sh => em_reports_consume.sh} (94%) mode change 100755 => 100644 diff --git a/docker/paperless/plugins/consume.sh b/docker/paperless/plugins/em_reports_consume.sh old mode 100755 new mode 100644 similarity index 94% rename from docker/paperless/plugins/consume.sh rename to docker/paperless/plugins/em_reports_consume.sh index 8737035..502f910 --- a/docker/paperless/plugins/consume.sh +++ b/docker/paperless/plugins/em_reports_consume.sh @@ -1,7 +1,7 @@ #!/bin/bash SRC="/volume1/docker/sharedata/stock_data/pdfs" DST="/volume1/docker/sharedata/stock_data/em_reports_consume" -LOG="./log/paperless.log" +LOG="/volume1/docker/projects/devops/docker/paperless/plugins/log/paperless.log" TARGET_UID=1000 TARGET_GID=1000 From 2b0e1c04133483a6ccd9ccd1dd21793b796a889b Mon Sep 17 00:00:00 2001 From: sophon Date: Sun, 11 Jan 2026 11:50:55 +0800 Subject: [PATCH 3/3] modify scripts --- docker/paperless/plugins/docker_patch.sh | 172 +++++++++++++----- .../{bak_parsers.py => origin_parsers.py} | 0 docker/paperless/plugins/readme.md | 37 ++++ docker/paperless/plugins/redme.txt | 80 -------- 4 files changed, 161 insertions(+), 128 deletions(-) rename docker/paperless/plugins/{bak_parsers.py => origin_parsers.py} (100%) mode change 100755 => 100644 create mode 100644 docker/paperless/plugins/readme.md delete mode 100644 docker/paperless/plugins/redme.txt diff --git a/docker/paperless/plugins/docker_patch.sh b/docker/paperless/plugins/docker_patch.sh index cb1205a..ee9b5ca 100755 --- a/docker/paperless/plugins/docker_patch.sh +++ b/docker/paperless/plugins/docker_patch.sh @@ -1,73 +1,149 @@ #!/bin/bash -# 定义文件路径 -SOURCE_PARSE_FILENAME="/usr/src/paperless/git_scripts/parse_filename.py" -DEST_PARSE_FILENAME="/usr/src/paperless/scripts/parse_filename.py" +# 定义文件替换对（数组形式，格式：源文件 目标文件） +# 可按需添加/删除行，每行一组 源文件 目标文件 +FILE_PAIRS=( + "/usr/src/paperless/scripts/parsers.py" "/usr/src/paperless/src/paperless_tesseract/parsers.py" + # 示例：新增更多文件对 + #"/usr/src/paperless/git_scripts/parse_filename.py" "/usr/src/paperless/scripts/parse_filename.py" + # "/path/to/source/file3" "/path/to/dest/file3" + # "/path/to/source/file4" "/path/to/dest/file4" +) -SOURCE_PARSERS="/usr/src/paperless/git_scripts/parsers.py" -DEST_PARSERS="/usr/src/paperless/src/paperless_tesseract/parsers.py" - -# 检查文件是否存在 +# 检查所有文件是否存在（仅检查replace/check操作需要的文件） check_files_exist() { local missing=0 - for file in "$SOURCE_PARSE_FILENAME" "$DEST_PARSE_FILENAME" "$SOURCE_PARSERS" "$DEST_PARSERS"; do - if [ ! -f "$file" ]; then - echo "错误：文件不存在 - $file" - missing=1 + local pair_count=${#FILE_PAIRS[@]} + + # 遍历文件对（步长2：源文件、目标文件为一组） + for ((i=0; i $source 的差异 ---" + diff -u "$dest" "$source" || true # 无差异时不报错 + done } -# 备份并替换文件 -replace_files() { - # 备份目标文件 - backup_file "$DEST_PARSE_FILENAME" - backup_file "$DEST_PARSERS" - - # 执行替换 - cp -f "$SOURCE_PARSE_FILENAME" "$DEST_PARSE_FILENAME" - cp -f "$SOURCE_PARSERS" "$DEST_PARSERS" - - echo -e "\n=== 替换完成，以下是替换后的差异（应无差异） ===" - show_diffs -} - -# 备份文件（添加 .bak 后缀，保留原权限） +# 备份单个文件（添加 .bak 后缀，保留原权限） backup_file() { local file="$1" local backup="$file.bak" + if [ -f "$backup" ]; then - # 若已有备份，先删除旧备份（避免累积过多） + echo "提示：旧备份文件已存在，将覆盖 - $backup" rm -f "$backup" fi - cp -a "$file" "$backup" # -a 保留权限和属性 + + cp -a "$file" "$backup" # -a 保留权限、属性、时间戳等 echo "已备份：$file -> $backup" } -# 主逻辑 -check_files_exist - -if [ "$1" = "check" ]; then - echo "=== 执行差异检查（不修改文件） ===" +# 替换所有文件对 +replace_files() { + local pair_count=${#FILE_PAIRS[@]} + echo "=== 开始替换文件（先备份目标文件） ===" + + for ((i=0; i $dest ---" + backup_file "$dest" + cp -f "$source" "$dest" + echo "已替换：$source 覆盖 $dest" + done + + echo -e "\n=== 替换完成，验证最终差异（应无差异） ===" show_diffs -elif [ "$1" = "replace" ]; then - echo "=== 执行文件替换（先备份） ===" - replace_files -else - echo "用法：$0 [check|replace]" - echo " check - 仅检查文件差异，不做修改" - echo " replace - 备份目标文件并替换，然后显示最终差异" - exit 1 -fi \ No newline at end of file +} + +# 回滚替换操作（恢复 .bak 备份文件） +rollback_files() { + local pair_count=${#FILE_PAIRS[@]} + echo "=== 开始回滚替换操作 ===" + + for ((i=0; i $dest ---" + if [ -f "$backup" ]; then + # 先备份当前文件（防止回滚出错） + cp -a "$dest" "$dest.rollback_temp" 2>/dev/null || true + # 恢复备份文件 + mv -f "$backup" "$dest" + echo "已回滚：$dest 恢复为备份版本" + # 删除临时文件 + rm -f "$dest.rollback_temp" 2>/dev/null || true + else + echo "跳过：备份文件不存在 - $backup" + fi + done + + echo -e "\n=== 回滚操作执行完成 ===" +} + +# 主逻辑 +main() { + case "$1" in + check) + echo "=== 执行文件差异检查（不修改文件） ===" + check_files_exist "check" + show_diffs + ;; + replace) + echo "=== 执行文件替换操作（自动备份） ===" + check_files_exist "replace" + replace_files + ;; + rollback) + echo "=== 执行文件回滚操作（恢复备份） ===" + check_files_exist "rollback" + rollback_files + ;; + *) + echo "用法：$0 [check|replace|rollback]" + echo " check - 仅检查所有文件对的差异，不做修改" + echo " replace - 备份所有目标文件并执行替换，完成后验证差异" + echo " rollback - 回滚替换操作（恢复 .bak 备份文件）" + exit 1 + ;; + esac +} + +# 启动主逻辑 +main "$1" \ No newline at end of file diff --git a/docker/paperless/plugins/bak_parsers.py b/docker/paperless/plugins/origin_parsers.py old mode 100755 new mode 100644 similarity index 100% rename from docker/paperless/plugins/bak_parsers.py rename to docker/paperless/plugins/origin_parsers.py diff --git a/docker/paperless/plugins/readme.md b/docker/paperless/plugins/readme.md new file mode 100644 index 0000000..cc987be --- /dev/null +++ b/docker/paperless/plugins/readme.md @@ -0,0 +1,37 @@ +## 登陆 +### 用户名： admin +### 密码： paperless + +## 需要指定用户名 +### 配置好 USERMAP_GID和USERMAP_GID，否则可能无法执行主机映射进去的脚本。 +### 详见 https://docs.paperless-ngx.com/configuration/#USERMAP_UID + +## 自定义的文件名解析脚本 +```Bash +# 文档 +https://docs.paperless-ngx.com/advanced_usage/#file-name-handling +https://docs.paperless-ngx.com/configuration/#PAPERLESS_POST_CONSUME_SCRIPT + +# 配置 +environment: + PAPERLESS_POST_CONSUME_SCRIPT: "/usr/src/paperless/scripts/parse_filename.py" +``` + + +## 源码修改，可以通过在容器里执行 docker_patch.sh 脚本来完成 +### 对于无法简单读取pdf内容的文档，paperless会启动OCR扫描，且复杂情况下会执行两遍，非常慢而且消耗资源。只能通过修改源码解决： +```Bash +# /usr/src/paperless/src/paperless_tesseract/parsers.py : + + # force skip ocr process. + if not original_has_text: + original_has_text = True + text_original = "this is default content, as we skipped ocr process..." + self.log.warning("Cannot read text from Document, use default message.") + + if skip_archive_for_text and original_has_text: + self.log.debug("Document has text, skipping OCRmyPDF entirely.") + self.text = text_original + return + +``` diff --git a/docker/paperless/plugins/redme.txt b/docker/paperless/plugins/redme.txt deleted file mode 100644 index dc3eb76..0000000 --- a/docker/paperless/plugins/redme.txt +++ /dev/null @@ -1,80 +0,0 @@ - - --------------------------------------------------------｜ -------------------- paperless 无纸化pdf管理 ------------｜ --------------------------------------------------------｜ - -## 最好不要用命令，使用docker-compose.yml来创建，需要制定后端使用的数据库，以及redis！ -docker run -itd \ - --name paperless \ - --network devops \ - --platform linux/x86_64 \ - -e TZ="Asia/Shanghai" \ - -v /etc/localtime:/etc/localtime:ro \ - -v "$(pwd)/dockers/paperless/pdfs:/usr/src/paperless/data" \ - -v "$(pwd)/dockers/paperless/db:/usr/src/paperless/db" \ - -e USERMAP_UID=1000 -e USERMAP_GID=1000 \ - -p 8000:8000 \ - ghcr.io/paperless-ngx/paperless-ngx - - -# 容器创建好之后，要手动设置密码（二选一操作，目前设置的 admin / admin） -docker compose run --rm webserver createsuperuser -python3 manage.py createsuperuser - -# 已有文档，放在指定目录下，等系统自动加载(或者手工启动) -cd /path/to/paperless/src/ -python3 manage.py document_consumer - -# 自动解析文件名 -https://docs.paperless-ngx.com/advanced_usage/#file-name-handling -https://docs.paperless-ngx.com/configuration/#PAPERLESS_POST_CONSUME_SCRIPT - -environment: - PAPERLESS_POST_CONSUME_SCRIPT: "/usr/src/paperless/scripts/parse_filename.py" - - -对于无法简单读取pdf内容的文档，paperless会启动OCR扫描，且复杂情况下会执行两遍，非常慢而且消耗资源。只能通过修改源码解决： -/usr/src/paperless/src/paperless_tesseract/parsers.py : - - # force skip ocr process. - if not original_has_text: - original_has_text = True - text_original = "this is default content, as we skipped ocr process..." - self.log.warning("Cannot read text from Document, use default message.") - - if skip_archive_for_text and original_has_text: - self.log.debug("Document has text, skipping OCRmyPDF entirely.") - self.text = text_original - return - - - -paperless 默认不会删除重复的文件，这会导致如果重复添加，会不停扫描，加载，报错。没找到配置，直接修改源码解决：（已经有配置，详见 docker-compose.yml） - -/usr/src/paperless/src/documents/consumer.py - - def pre_check_duplicate(self): - """ - Using the MD5 of the file, check this exact file doesn't already exist - """ - with open(self.input_doc.original_file, "rb") as f: - checksum = hashlib.md5(f.read()).hexdigest() - existing_doc = Document.global_objects.filter( - Q(checksum=checksum) | Q(archive_checksum=checksum), - ) - if existing_doc.exists(): - msg = ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS - log_msg = f"Not consuming {self.filename}: It is a duplicate of {existing_doc.get().title} (#{existing_doc.get().pk})." - - if existing_doc.first().deleted_at is not None: - msg = ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS_IN_TRASH - log_msg += " Note: existing document is in the trash." - - ## 修改这里，让它删除重复文件。 - if settings.CONSUMER_DELETE_DUPLICATES or True: - os.unlink(self.input_doc.original_file) - self._fail( - msg, - log_msg, - )