Обновить projdump.sh

2026-03-11 15:40:46 +07:00
parent 51a38bbeba
commit 7d93bf8d18
1 changed files with 178 additions and 35 deletions
--- a/projdump.sh
+++ b/projdump.sh
@@ -3,24 +3,40 @@

 set -euo pipefail

+# ── Настройки (можно менять) ─────────────────────────────────────────────────
+MAX_FILE_SIZE_KB=100          # Пропускать файлы больше этого размера (КБ)
+TRUNCATE_LINES=2000           # Обрезать файлы длиннее этого кол-ва строк
+# ─────────────────────────────────────────────────────────────────────────────
+
 usage() {
    cat >&2 <<EOF
-Использование: $0 <директория>
+Использование: $0 [опции] <директория>

 Создаёт один файл:
-  <basename>-dump.txt — дерево проекта + содержимое файлов (без MD-разметки)
+  <basename>-dump.txt — дерево проекта + содержимое файлов

-Параметры:
+Опции:
+  -s, --max-size КБ     Макс. размер файла в КБ (по умолчанию: $MAX_FILE_SIZE_KB)
+  -l, --max-lines N      Обрезать после N строк (по умолчанию: $TRUNCATE_LINES)
  -h, --help             Показать эту справку
 EOF
 }

-if [[ $# -eq 0 ]] || [[ "$1" == "-h" ]] || [[ "$1" == "--help" ]]; then
-    usage
-    exit 0
-fi
+# ── Парсинг аргументов ───────────────────────────────────────────────────────
+while [[ $# -gt 0 ]]; do
+    case "$1" in
+        -s|--max-size)  MAX_FILE_SIZE_KB="$2"; shift 2 ;;
+        -l|--max-lines) TRUNCATE_LINES="$2"; shift 2 ;;
+        -h|--help)      usage; exit 0 ;;
+        -*)             echo "Неизвестная опция: $1" >&2; usage; exit 1 ;;
+        *)              TARGET_DIR="$1"; shift ;;
+    esac
+done

-TARGET_DIR="$1"
+if [[ -z "${TARGET_DIR:-}" ]]; then
+    usage
+    exit 1
+fi

 if [[ ! -d "$TARGET_DIR" ]]; then
    echo "Ошибка: директория '$TARGET_DIR' не существует." >&2
@@ -35,24 +51,67 @@ if ! command -v tree >/dev/null 2>&1; then
    exit 1
 fi

-# Список игнорирования (оставлен без изменений)
+# ── Игнорируемые директории и файлы ──────────────────────────────────────────
 IGNORE_LIST=(
-    "third_party" "3rd_party" "3rdparty" ".git" ".svn" ".hg" "node_modules" 
-    "__pycache__" "*.pyc" ".venv" "venv" "env" ".env" ".idea" ".vscode" ".vs" 
-    ".DS_Store" "Thumbs.db" "dist" "build" "out" "target" ".pytest_cache" 
-    ".mypy_cache" ".next" ".nuxt" ".output" ".svelte-kit" "coverage" ".cache" 
-    ".parcel-cache" ".eslintcache" ".yarn" "yarn-error.log" "package-lock.json" 
-    "yarn.lock" "pnpm-lock.yaml" "Cargo.lock" "go.sum" ".gradle" "gradle" 
-    ".mvn" "mvnw" "mvnw.cmd" "*.swp" "*.swo" ".stack-work" "_build" "deps" 
-    ".cargo" ".rustup" ".clangd" ".ccls-cache" "CMakeFiles" "CMakeCache.txt" 
-    "CTestTestfile.cmake" "cmake_install.cmake" "*.dSYM" "*.ilk" "*.pdb" 
-    "*.obj" "*.o" "*.so" "*.dylib" "*.dll" "*.exe" "*.bin" "*.hex" "*.elf" 
-    "tags" "TAGS" "GPATH" "GTAGS" "GRTAGS" "GSYMS" ".github" ".gitlab" 
-    ".circleci" ".travis.yml" "Jenkinsfile" "Dockerfile*" "docker-compose*.yml" 
-    "*.log" "logs" "tmp" "temp" ".terraform" ".tfstate" ".tfstate.backup" "*.tfvars"
+    # VCS
+    ".git" ".svn" ".hg"
+    # Зависимости
+    "node_modules" "vendor" "third_party" "3rd_party" "3rdparty"
+    "bower_components" ".pnp" ".pnp.js"
+    # Python
+    "__pycache__" "*.pyc" "*.pyo" ".venv" "venv" "env" ".env"
+    ".mypy_cache" ".pytest_cache" ".ruff_cache" ".tox" "*.egg-info"
+    # IDE / редакторы
+    ".idea" ".vscode" ".vs" "*.swp" "*.swo" "*~"
+    # OS
+    ".DS_Store" "Thumbs.db" "desktop.ini"
+    # Сборка / выходные директории
+    "dist" "build" "out" "target" "_build" "release"
+    # JS / фронтенд
+    ".next" ".nuxt" ".output" ".svelte-kit" ".parcel-cache"
+    ".eslintcache" "coverage" ".cache" ".turbo"
+    # Lock-файлы
+    "package-lock.json" "yarn.lock" "pnpm-lock.yaml" "bun.lockb"
+    "Cargo.lock" "go.sum" "Gemfile.lock" "poetry.lock"
+    "composer.lock" "Pipfile.lock" "flake.lock"
+    # Yarn
+    ".yarn" "yarn-error.log"
+    # Java / Kotlin / Gradle / Maven
+    ".gradle" "gradle" ".mvn" "mvnw" "mvnw.cmd"
+    # Rust / Go / Haskell
+    ".cargo" ".rustup" ".stack-work" "deps"
+    # C / C++
+    ".clangd" ".ccls-cache" "CMakeFiles" "CMakeCache.txt"
+    "CTestTestfile.cmake" "cmake_install.cmake"
+    # Скомпилированные бинарники
+    "*.dSYM" "*.ilk" "*.pdb" "*.obj" "*.o" "*.so" "*.dylib"
+    "*.dll" "*.exe" "*.bin" "*.hex" "*.elf" "*.a" "*.lib" "*.class"
+    # Теги
+    "tags" "TAGS" "GPATH" "GTAGS" "GRTAGS" "GSYMS"
+    # CI / CD / Docker
+    ".github" ".gitlab" ".circleci" ".travis.yml"
+    "Jenkinsfile" "Dockerfile*" "docker-compose*.yml"
+    # Логи / временные
+    "*.log" "logs" "tmp" "temp"
+    # Terraform
+    ".terraform" ".tfstate" ".tfstate.backup" "*.tfvars"
+    # Минифицированные файлы
+    "*.min.js" "*.min.css" "*.min.map"
+    # Source maps
+    "*.map"
+    # Медиа / шрифты / бинарные ассеты
+    "*.png" "*.jpg" "*.jpeg" "*.gif" "*.bmp" "*.ico" "*.icns"
+    "*.webp" "*.avif" "*.svg" "*.mp3" "*.mp4" "*.avi" "*.mov"
+    "*.mkv" "*.wav" "*.flac" "*.ogg" "*.webm"
+    "*.woff" "*.woff2" "*.ttf" "*.otf" "*.eot"
+    "*.pdf" "*.doc" "*.docx" "*.xls" "*.xlsx" "*.ppt" "*.pptx"
+    "*.zip" "*.tar" "*.gz" "*.bz2" "*.xz" "*.7z" "*.rar"
+    "*.db" "*.sqlite" "*.sqlite3"
+    "*.jar" "*.war" "*.ear"
+    "*.iso" "*.dmg" "*.img"
 )

-# Подготовка аргументов для find
+# ── Подготовка аргументов для find ───────────────────────────────────────────
 FIND_IGNORE_ARGS=()
 for pat in "${IGNORE_LIST[@]}"; do
    if [[ "$pat" == */* ]]; then
@@ -64,7 +123,7 @@ done

 FIND_CMD=(find "$TARGET_DIR" \( -false "${FIND_IGNORE_ARGS[@]}" \) -prune -o -type f -print0)

-# Подготовка шаблонов для tree
+# ── Подготовка шаблонов для tree ─────────────────────────────────────────────
 TREE_IGNORE_PATTERNS=""
 for pat in "${IGNORE_LIST[@]}"; do
    base_pat="${pat%%/*}"
@@ -75,29 +134,113 @@ for pat in "${IGNORE_LIST[@]}"; do
    fi
 done

+# ── Проверка: текстовый ли файл ─────────────────────────────────────────────
+is_text_file() {
+    local f="$1"
+    local mime
+    mime=$(file --brief --mime-type "$f" 2>/dev/null || echo "unknown")
+    case "$mime" in
+        text/*|application/json|application/xml|application/javascript|\
+        application/x-shellscript|application/x-httpd-php|application/toml|\
+        application/x-yaml|application/x-ruby|application/x-perl|\
+        application/x-python|inode/x-empty)
+            return 0 ;;
+        *)
+            return 1 ;;
+    esac
+}
+
+# ── Форматирование размера ───────────────────────────────────────────────────
+human_size() {
+    local bytes=$1
+    if (( bytes < 1024 )); then
+        echo "${bytes} B"
+    elif (( bytes < 1048576 )); then
+        echo "$(( bytes / 1024 )) KB"
+    else
+        echo "$(awk "BEGIN {printf \"%.1f MB\", $bytes/1048576}")"
+    fi
+}
+
+# ── Генерация дампа ──────────────────────────────────────────────────────────
 OUTPUT_FILE="${BASENAME}-dump.txt"
+MAX_FILE_SIZE_BYTES=$(( MAX_FILE_SIZE_KB * 1024 ))
+
+FILE_COUNT=0
+SKIPPED_BINARY=0
+SKIPPED_SIZE=0
+TRUNCATED=0

 {
    echo "==============================================================================="
    echo "PROJECT NAME: $BASENAME"
    echo "GENERATED ON: $(date)"
+    echo "MAX FILE SIZE: ${MAX_FILE_SIZE_KB} KB"
+    echo "TRUNCATE AFTER: ${TRUNCATE_LINES} lines"
    echo "==============================================================================="
-    echo -e "\n--- PROJECT STRUCTURE ---"
+    echo ""
+    echo "--- PROJECT STRUCTURE ---"
    tree -n -I "$TREE_IGNORE_PATTERNS" "$TARGET_DIR"
-    echo -e "\n==============================================================================="
+    echo ""
+    echo "==============================================================================="
    echo "SOURCE CODE CONTENTS"
    echo "==============================================================================="

    while IFS= read -r -d '' file; do
-        # Относительный путь для красоты
        rel_path="${file#$TARGET_DIR/}"
+        file_size=$(stat -c%s "$file" 2>/dev/null || stat -f%z "$file" 2>/dev/null || echo 0)

-        echo -e "\nFILE: $rel_path"
+        # Проверка размера
+        if (( file_size > MAX_FILE_SIZE_BYTES )); then
+            echo ""
+            echo "FILE: $rel_path  ($(human_size "$file_size"))"
            echo "-------------------------------------------------------------------------------"
+            echo "[SKIPPED — file exceeds ${MAX_FILE_SIZE_KB} KB limit]"
+            echo "-------------------------------------------------------------------------------"
+            (( SKIPPED_SIZE++ ))
+            continue
+        fi
+
+        # Проверка: текстовый ли
+        if ! is_text_file "$file"; then
+            (( SKIPPED_BINARY++ ))
+            continue
+        fi
+
+        line_count=$(wc -l < "$file" || echo 0)
+        FILE_COUNT=$(( FILE_COUNT + 1 ))
+
+        echo ""
+        echo "FILE: $rel_path  (${line_count} lines, $(human_size "$file_size"))"
+        echo "-------------------------------------------------------------------------------"
+
+        if (( line_count > TRUNCATE_LINES )); then
+            head -n "$TRUNCATE_LINES" "$file"
+            echo ""
+            echo "[TRUNCATED — showing first ${TRUNCATE_LINES} of ${line_count} lines]"
+            (( TRUNCATED++ ))
+        else
            cat "$file"
-        echo -e "\n-------------------------------------------------------------------------------"
-        echo "END OF FILE: $rel_path"
-    done < <("${FIND_CMD[@]}")
+        fi
+
+        echo ""
+        echo "-------------------------------------------------------------------------------"
+    done < <("${FIND_CMD[@]}" | sort -z)
+
+    echo ""
+    echo "==============================================================================="
+    echo "SUMMARY"
+    echo "==============================================================================="
+    echo "Files included:       $FILE_COUNT"
+    echo "Skipped (binary):     $SKIPPED_BINARY"
+    echo "Skipped (too large):  $SKIPPED_SIZE"
+    echo "Truncated:            $TRUNCATED"
+    echo "==============================================================================="
 } > "$OUTPUT_FILE"

 echo "Готово: $OUTPUT_FILE"
+echo "  Файлов включено:        $FILE_COUNT"
+echo "  Пропущено (бинарные):   $SKIPPED_BINARY"
+echo "  Пропущено (большие):    $SKIPPED_SIZE"
+echo "  Обрезано:               $TRUNCATED"
+echo "  Размер дампа:           $(human_size "$(stat -c%s "$OUTPUT_FILE" 2>/dev/null || stat -f%z "$OUTPUT_FILE")")"